"기계 학습"의 두 판 사이의 차이

수학노트
둘러보기로 가기 검색하러 가기
 
(같은 사용자의 중간 판 35개는 보이지 않습니다)
1번째 줄: 1번째 줄:
 
==개요==
 
==개요==
* 컴퓨터 과학의 핵심 과제 중 하나는 컴퓨터에게 수행 방법을 알려주지 않고 수행해야 하는 작업을 수행하도록 하는 것이다.
+
* 컴퓨터 과학의 핵심 과제 중 하나는 컴퓨터에게 수행 방법을 명시적으로 알려주지 않고 작업을 수행하도록 하는 것이다.
* 많은 경우 작업은 매개변수가 있는 수학적 모델로 기술된다
+
* 많은 경우 작업은 매개변수가 있는 수학적 모델로 기술된다.
* 이러한 모델의 매개변수는 일반적으로 알려져 있지 않으며 통계적 방법을 사용하여 데이터에서 추정해야 한다.
+
* 이러한 모델의 매개변수는 통계적 방법을 사용하여 데이터에서 추정해야 한다.
 +
* 기계 학습이란 이 매개변수를 찾아가는 과정이라 할 수 있다.
 
* fundamental problems in machine learning
 
* fundamental problems in machine learning
 
** regression
 
** regression
8번째 줄: 9번째 줄:
 
** [[차원축소]]
 
** [[차원축소]]
 
** probability density estimation
 
** probability density estimation
 +
* 기계 학습은 시스템에서 학습을 위해 사용하는 피드백의 특성에 따라 보통 다음의 세 가지 범주로 나누어진다:
 +
** [[지도 학습]]
 +
** [[비지도 학습]]
 +
** [[강화 학습]]
  
 
==관련된 항목들==
 
==관련된 항목들==
 +
* [[인공지능]]
 +
* [[회귀와 분류]]
 
* [[선형 회귀]]
 
* [[선형 회귀]]
 
* [[로지스틱 회귀]]
 
* [[로지스틱 회귀]]
23번째 줄: 30번째 줄:
 
* [[서포트 벡터 머신]]
 
* [[서포트 벡터 머신]]
 
* [[K-평균 알고리즘]]
 
* [[K-평균 알고리즘]]
 +
* [[Kernel regression]]
 
* [[Gaussian mixture model]]
 
* [[Gaussian mixture model]]
 +
* [[Radial basis function]]
 
* [[DBSCAN]]
 
* [[DBSCAN]]
 +
* [[토픽 모델링]]
 
* [[주성분 분석]]
 
* [[주성분 분석]]
 
* [[특이값 분해]]
 
* [[특이값 분해]]
33번째 줄: 43번째 줄:
 
* [[유전 프로그래밍]]
 
* [[유전 프로그래밍]]
 
* [[Symbolic regression]]
 
* [[Symbolic regression]]
 +
* [[Gradient boosting]]
 
* [[그래프 모형]]
 
* [[그래프 모형]]
 
* [[쿨백-라이블러 발산]]
 
* [[쿨백-라이블러 발산]]
* [[Activation function]]
+
* [[활성화 함수]]
 
* [[ReLU]]
 
* [[ReLU]]
 +
* [[퍼셉트론]]
 +
* [[ADALINE]]
 +
* [[경사 하강법]]
 +
* [[확률적 경사 하강법]]
 +
* [[오차역전파법]]
 +
* [[손실 함수]]
 +
* [[Pooling]]
 +
* [[Vanishing gradient problem]]
 +
* [[딥 러닝]]
 +
* [[인공 신경망]]
 
* [[합성곱 신경망]]
 
* [[합성곱 신경망]]
 
* [[순환 인공 신경망]]
 
* [[순환 인공 신경망]]
 +
* [[인공 신경망의 층]]
 
* [[Long Short-Term Memory]]
 
* [[Long Short-Term Memory]]
 
* [[Gated recurrent unit]]
 
* [[Gated recurrent unit]]
 +
* [[Autoencoder]]
 
* [[생성적 적대 신경망]]
 
* [[생성적 적대 신경망]]
 +
* [[Deep Q-Network]]
 
* [[LeNet-5]]
 
* [[LeNet-5]]
 
* [[AlexNet]]
 
* [[AlexNet]]
 
* [[VGGNet]]
 
* [[VGGNet]]
 
* [[GoogLeNet]]
 
* [[GoogLeNet]]
 +
* [[BERT]]
 
* [[Residual neural network]]
 
* [[Residual neural network]]
 
* [[Differentiable neural computer]]
 
* [[Differentiable neural computer]]
 
* [[자연어 처리]]
 
* [[자연어 처리]]
 
* [[컴퓨터 비전]]
 
* [[컴퓨터 비전]]
 +
* [[OpenCV]]
 
* [[영상 처리]]
 
* [[영상 처리]]
 
* [[지도 학습]]
 
* [[지도 학습]]
57번째 줄: 83번째 줄:
 
* [[음성 인식]]
 
* [[음성 인식]]
 
* [[음성 합성]]
 
* [[음성 합성]]
 +
* [[이미지 분류]]
 +
* [[객체 인식]]
 +
* [[안면 인식 시스템]]
 +
* [[동작 인식]]
 +
* [[기계 번역]]
 +
* [[추천 시스템]]
 +
* [[협업 필터링]]
 +
* [[가짜뉴스|가짜뉴스 탐지]]
 +
* [[개체명 인식]]
 +
* [[스팸 필터]]
 +
* [[Chainer]]
 +
* [[TensorFlow]]
 +
* [[케라스]]
 +
* [[PyTorch]]
 +
* [[Theano]]
 +
* [[Caret]]
 +
* [[Scikit-learn]]
 +
* [[데이터 사이언스]]
 +
* [[캐글]]
 +
* [[Iris flower data set]]
 +
* [[MNIST 데이터베이스]]
 +
* [[CIFAR-10]]
 +
* [[CIFAR-100]]
 +
* [[IMDB 데이터셋]]
  
 
== 노트 ==
 
== 노트 ==
  
* It is problems like this which machine learning is trying to solve.<ref name="ref_b8d4">[https://www.bernardmarr.com/default.asp?contentID=1140 What Is Machine Learning - A Complete Beginner's Guide]</ref>
+
===위키데이터===
* “Deep learning” – another hot topic buzzword – is simply machine learning which is derived from “deep” neural nets.<ref name="ref_b8d4" />
+
* ID :  [https://www.wikidata.org/wiki/Q2539 Q2539]
* Without a doubt, machine learning is proving itself to be a technology with far-reaching transformative powers.<ref name="ref_b8d4" />
+
===말뭉치===
* Machine learning is the key which has unlocked it, and its potential future applications are almost unlimited.<ref name="ref_b8d4" />
+
# If you are a newbie in machine learning you may have thought that what programming language should I learn?<ref name="ref_802cb889">[https://www.geeksforgeeks.org/top-5-programming-languages-and-their-libraries-for-machine-learning-in-2020/ Top 5 Programming Languages and their Libraries for Machine Learning in 2020]</ref>
* Machine learning brings together computer science and statistics to harness that predictive power.<ref name="ref_20d2">[https://www.udacity.com/course/intro-to-machine-learning--ud120 Introduction to Machine Learning Course]</ref>
+
# Machine Learning is one of the fastest-growing fields which has witnessed an exponential growth in the technical world.<ref name="ref_802cb889" />
* The past decade has brought tremendous advances in an exciting dimension of artificial intelligence—machine learning.<ref name="ref_9a36">[https://hbr.org/2020/09/how-to-win-with-machine-learning How to Win with Machine Learning]</ref>
+
# Python leads all the other languages with more than 60% of machine learning developers are using and prioritising it for development because python is easy to learn.<ref name="ref_802cb889" />
* A prediction, in the context of machine learning, is an information output that comes from entering some data and running an algorithm.<ref name="ref_9a36" />
+
# This programming language is the “Jack of all the trade” and continues to dominate over in the ML industry also.<ref name="ref_802cb889" />
* It can also be dangerously easy to introduce biases into machine learning, especially if multiple factors are in play.<ref name="ref_9a36" />
+
# Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.<ref name="ref_c417bfce">[https://www.expert.ai/blog/machine-learning-definition/ What is Machine Learning? A definition - Expert System]</ref>
* In many ways, building a sustainable business in machine learning is much like building a sustainable business in any industry.<ref name="ref_9a36" />
+
# Supervised machine learning algorithms can apply what has been learned in the past to new data using labeled examples to predict future events.<ref name="ref_c417bfce" />
* For example, machine learning can reveal customers who are likely to churn, likely fraudulent insurance claims, and more.<ref name="ref_e67f">[https://www.datarobot.com/wiki/machine-learning/ DataRobot Artificial Intelligence Wiki]</ref>
+
# In contrast, unsupervised machine learning algorithms are used when the information used to train is neither classified nor labeled.<ref name="ref_c417bfce" />
* Companies that effectively implement machine learning and other AI technologies gain a massive competitive advantage.<ref name="ref_e67f" />
+
# Reinforcement machine learning algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards.<ref name="ref_c417bfce" />
* Machine learning could also be used for security applications, such as analysing email communications or internet usage.<ref name="ref_92e2">[https://royalsociety.org/topics-policy/projects/machine-learning/videos-and-background-information/ What is machine learning?]</ref>
+
# To help those interested in the field better understand how to break into a career in machine learning, we compiled the most important details and resources.<ref name="ref_b0912c82">[https://www.techrepublic.com/article/how-to-become-a-machine-learning-engineer-a-cheat-sheet/ How to become a machine learning engineer: A cheat sheet]</ref>
* The project will focus on current and near-term (5-10 years) applications of machine learning.<ref name="ref_92e2" />
+
# In terms of specific positions, 94% of job postings that contained AI or machine learning terminology were for machine learning engineers, the report found.<ref name="ref_b0912c82" />
* The above definition encapsulates the ideal objective or ultimate aim of machine learning, as expressed by many researchers in the field.<ref name="ref_f584">[https://emerj.com/ai-glossary-terms/what-is-machine-learning/ What is Machine Learning?]</ref>
+
# "Software is eating the world and machine learning is eating software," Vitaly Gordon, vice president of data science and software engineering for Salesforce Einstein, told TechRepublic.<ref name="ref_b0912c82" />
* As with any concept, machine learning may have a slightly different definition, depending on whom you ask.<ref name="ref_f584" />
+
# "Machine learning engineering is a discipline that requires production grade coding, PhD level machine learning, and the business acumen of a product manager.<ref name="ref_b0912c82" />
* – Stanford “Machine learning is based on algorithms that can learn from data without relying on rules-based programming.<ref name="ref_f584" />
+
# So, can machine learning be self-taught?<ref name="ref_c495f2ec">[https://mlcorner.com/can-machine-learning-be-self-taught/ Can machine learning be self-taught?]</ref>
* Emerj helps businesses get started with artificial intelligence and machine learning.<ref name="ref_f584" />
+
# Even though there are many different skills to learn in machine learning it is possible for you to self-teach yourself machine learning.<ref name="ref_c495f2ec" />
* Funding for research and development in the fields of machine learning and artificial intelligence is growing at a rapid pace.<ref name="ref_ca00">[https://www.edx.org/learn/machine-learning Learn Machine Learning with Online Courses and Classes]</ref>
+
# There are actually so many machine learning courses available now that choosing the right path for you can be quite daunting.<ref name="ref_c495f2ec" />
* The field of machine learning is booming and having the right skills and experience can help you get a path to a lucrative career.<ref name="ref_ca00" />
+
# course is that it will give you the chance to see if machine learning is something that you are actually interested in.<ref name="ref_c495f2ec" />
* From Apple to Google to Toyota, companies across the world are pouring resources into developing AI systems with machine learning.<ref name="ref_c74f">[https://www.techrepublic.com/article/machine-learning-the-smart-persons-guide/ Machine learning: A cheat sheet]</ref>
+
# which statuses you are reacting to—and using machine learning to make a highly educated guess about what you might want next.<ref name="ref_eb1c5a86">[https://www.technologyreview.com/2018/11/17/103781/what-is-machine-learning-we-drew-you-another-flowchart/ What is machine learning?]</ref>
* While there are different forms of AI, machine learning (ML) represents today's most widely valued mechanism for reaching intelligence.<ref name="ref_c74f" />
+
# Deep learning is machine learning on steroids: it uses a technique that gives machines an enhanced ability to find—and amplify—even the smallest patterns.<ref name="ref_eb1c5a86" />
* Machine learning became popular in the 1990s, and returned to the public eye when Google's DeepMind beat the world champion of Go in 2016.<ref name="ref_c74f" />
+
# In machine learning, algorithms are 'trained' to find patterns and features in massive amounts of data in order to make decisions and predictions based on new data.<ref name="ref_84891f0c">[https://www.ibm.com/cloud/learn/machine-learning What is Machine Learning?]</ref>
* Since then, ML applications and machine learning's popularity have only increased.<ref name="ref_c74f" />
+
# There are four basic steps for building a machine learning application (or model).<ref name="ref_84891f0c" />
* ML is one of the most exciting technologies that one would have ever come across.<ref name="ref_3ac7">[https://www.geeksforgeeks.org/machine-learning/ Machine Learning]</ref>
+
# Training data is a data set representative of the data the machine learning model will ingest to solve the problem it’s designed to solve.<ref name="ref_84891f0c" />
* Machine learning is a branch of artificial intelligence that includes methods, or algorithms, for automatically creating models from data.<ref name="ref_18d2">[https://www.infoworld.com/article/3214424/what-is-machine-learning-intelligence-derived-from-data.html What is machine learning? Intelligence derived from data]</ref>
+
# Supervised machine learning trains itself on a labeled data set.<ref name="ref_84891f0c" />
* Game-playing machine learning is strongly successful for checkers, chess, shogi, and Go, having beaten human world champions.<ref name="ref_18d2" />
+
# Machine learning is a branch of artificial intelligence that includes methods, or algorithms, for automatically creating models from data.<ref name="ref_18d285db">[https://www.infoworld.com/article/3214424/what-is-machine-learning-intelligence-derived-from-data.html What is machine learning? Intelligence derived from data]</ref>
* Machine learning depends on a number of algorithms for turning a data set into a model.<ref name="ref_18d2" />
+
# Unlike a system that performs a task by following explicit rules, a machine learning system learns from experience.<ref name="ref_18d285db" />
* As with all machine learning, you need to check the predictions of the neural network against a separate test data set.<ref name="ref_18d2" />
+
# We hear about applications of machine learning on a daily basis, although not all of them are unalloyed successes.<ref name="ref_18d285db" />
* A diverse community of developers, enterprises and researchers are using ML to solve challenging, real-world problems.<ref name="ref_1df9">[https://www.tensorflow.org/ TensorFlow]</ref>
+
# Game-playing machine learning is strongly successful for checkers, chess, shogi, and Go, having beaten human world champions.<ref name="ref_18d285db" />
* Natural Language Derive insights from unstructured text using Google machine learning.<ref name="ref_f60c">[https://cloud.google.com/products/ai Google Cloud]</ref>
+
# Machine learning is one modern innovation that has helped man enhance not only many industrial and professional processes but also advances everyday living.<ref name="ref_5a500f58">[https://bigdata-madesimple.com/top-10-real-life-examples-of-machine-learning/ Top 10 real-life examples of Machine Learning]</ref>
* Translation Dynamically translate between languages using Google machine learning.<ref name="ref_f60c" />
+
# But what is machine learning?<ref name="ref_5a500f58" />
* A very important group of algorithms for both supervised and unsupervised machine learning are neural networks.<ref name="ref_d9f6">[https://www.zdnet.com/article/what-is-machine-learning-everything-you-need-to-know/ What is machine learning? Everything you need to know]</ref>
+
# Currently, machine learning has been used in multiple fields and industries.<ref name="ref_5a500f58" />
* DeepMind continue to break new ground in the field of machine learning.<ref name="ref_d9f6" />
+
# The intelligent systems built on machine learning algorithms have the capability to learn from past experience or historical data.<ref name="ref_5a500f58" />
* But beyond these very visible manifestations of machine learning, systems are starting to find a use in just about every industry.<ref name="ref_d9f6" />
+
# Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so.<ref name="ref_8ed88b93">[https://searchenterpriseai.techtarget.com/definition/machine-learning-ML What is Machine learning (ML)?]</ref>
* Machine learning enables analysis of massive quantities of data.<ref name="ref_638d">[https://www.expert.ai/blog/machine-learning-definition/ What is Machine Learning? A definition - Expert System]</ref>
+
# Types of machine learning Classical machine learning is often categorized by how an algorithm learns to become more accurate in its predictions.<ref name="ref_8ed88b93" />
* The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning.<ref name="ref_3370">[https://en.wikipedia.org/wiki/Machine_learning Machine learning]</ref>
+
# this type of machine learning, data scientists supply algorithms with training data and define the variables they want the algorithm to assess for correlations.<ref name="ref_8ed88b93" />
* Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so.<ref name="ref_3370" />
+
# This type of machine learning involves algorithms that train on unlabeled data.<ref name="ref_8ed88b93" />
* As a scientific endeavor, machine learning grew out of the quest for artificial intelligence.<ref name="ref_3370" />
+
# Similar drag and drop modules have been added to Azure Machine Learning designer.<ref name="ref_d57b6569">[https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/machine-learning-score ML Studio (classic): Machine Learning Scoring - Azure]</ref>
* However, an increasing emphasis on the logical, knowledge-based approach caused a rift between AI and machine learning.<ref name="ref_3370" />
+
# Scoring is also called prediction, and is the process of generating values based on a trained machine learning model, given some new input data.<ref name="ref_d57b6569" />
* In machine learning, a situation in which a model's predictions influence the training data for the same model or another model.<ref name="ref_263c">[https://developers.google.com/machine-learning/glossary Machine Learning Glossary]</ref>
+
# Machine Learning Studio (classic) supports a flexible, customizable framework for machine learning.<ref name="ref_d57b6569" />
* More typically in machine learning, a hyperplane is the boundary separating a high-dimensional space.<ref name="ref_263c" />
+
# In this phase of machine learning, you apply a trained model to new data, to generate predictions.<ref name="ref_d57b6569" />
* An i.i.d. is the ideal gas of machine learning—a useful mathematical construct but almost never exactly found in the real world.<ref name="ref_263c" />
+
# Some machine learning algorithms are described as “supervised” machine learning algorithms as they are designed for supervised machine learning problems.<ref name="ref_742e774f">[https://machinelearningmastery.com/types-of-learning-in-machine-learning/ 14 Different Types of Learning in Machine Learning]</ref>
* In machine learning, often refers to the process of making predictions by applying the trained model to unlabeled examples.<ref name="ref_263c" />
+
# Some machine learning algorithms do not just experience a fixed dataset.<ref name="ref_742e774f" />
* The main intend of machine learning is to build a model that performs well on both the training set and the test set.<ref name="ref_88b0">[https://www.sciencedirect.com/topics/computer-science/machine-learning Machine Learning - an overview]</ref>
+
# Fitting a machine learning model is a process of induction.<ref name="ref_742e774f" />
* Machine learning is the concept that a computer program can learn and adapt to new data without human intervention.<ref name="ref_b833">[https://www.investopedia.com/terms/m/machine-learning.asp Machine Learning]</ref>
+
# In the context of machine learning, once we use induction to fit a model on a training dataset, the model can be used to make predictions.<ref name="ref_742e774f" />
* The various data applications of machine learning are formed through a complex algorithm or source code built into the machine or computer.<ref name="ref_b833" />
+
# A very important group of algorithms for both supervised and unsupervised machine learning are neural networks.<ref name="ref_d9f64b49">[https://www.zdnet.com/article/what-is-machine-learning-everything-you-need-to-know/ What is machine learning? Everything you need to know]</ref>
* Machine learning is used in different sectors for various reasons.<ref name="ref_b833" />
+
# For instance, consider the example of using machine learning to recognize handwritten numbers between 0 and 9.<ref name="ref_d9f64b49" />
* The supply of able ML designers has yet to catch up to this demand.<ref name="ref_175c">[https://www.toptal.com/machine-learning/machine-learning-theory-an-introductory-primer An Introduction to Machine Learning Theory and Its Applications: A Visual Tutorial with Examples]</ref>
+
# As the use of machine learning has taken off, so companies are now creating specialized hardware tailored to running and training machine-learning models.<ref name="ref_d9f64b49" />
* Determining which inputs to use is an important part of ML design.<ref name="ref_175c" />
+
# In 2020, Google said its fourth-generation TPUs were 2.7 times faster than previous gen TPUs in MLPerf, a benchmark which measures how fast a system can carry out inference using a trained ML model.<ref name="ref_d9f64b49" />
* The goal of ML is never to make “perfect” guesses, because ML deals in domains where there is no such thing.<ref name="ref_175c" />
+
# 📚 Check out our editorial recommendations on the best machine learning books.<ref name="ref_58e6771e">[https://medium.com/towards-artificial-intelligence/top-universities-to-pursue-a-masters-in-machine-learning-ml-in-the-us-ai-d4a461229fbb Best Masters Programs in Machine Learning (ML) for 2020]</ref>
* Fortunately, the iterative approach taken by ML systems is much more resilient in the face of such complexity.<ref name="ref_175c" />
+
# next → ← prev Applications of Machine learning Machine learning is a buzzword for today's technology, and it is growing very rapidly day by day.<ref name="ref_0c40f9d2">[https://www.javatpoint.com/applications-of-machine-learning Applications of Machine learning]</ref>
* – Make revolutionary advances in machine learning and AI.<ref name="ref_7927">[https://machinelearningmastery.com/what-is-deep-learning/ What is Deep Learning?]</ref>
+
# We are using machine learning in our daily life even without knowing it such as Google Maps, Google assistant, Alexa, etc.<ref name="ref_0c40f9d2" />
* Machine learning and AI are often discussed together, and the terms are sometimes used interchangeably, but they don’t mean the same thing.<ref name="ref_4ea3">[https://www.oracle.com/data-science/machine-learning/what-is-machine-learning/ What is machine learning?]</ref>
+
# Below are some most trending real-world applications of Machine Learning: 1.<ref name="ref_0c40f9d2" />
* Machine learning and the technology around it are developing rapidly, and we're just beginning to scratch the surface of its capabilities.<ref name="ref_4ea3" />
+
# While using Google, we get an option of "Search by voice," it comes under speech recognition, and it's a popular application of machine learning.<ref name="ref_0c40f9d2" />
* All ML tasks can be represented this way, or it's not an ML problem from the beginning.<ref name="ref_45cd">[https://vas3k.com/blog/machine_learning/ Machine Learning for Everyone]</ref>
+
# A subset of machine learning is closely related to computational statistics, which focuses on making predictions using computers; but not all machine learning is statistical learning.<ref name="ref_07a59b21">[https://en.wikipedia.org/wiki/Machine_learning Machine learning]</ref>
* That's why selecting the right features usually takes way longer than all the other ML parts.<ref name="ref_45cd" />
+
# The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning.<ref name="ref_07a59b21" />
* That's why the phrase "will neural nets replace machine learning" sounds like "will the wheels replace cars".<ref name="ref_45cd" />
+
# Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so.<ref name="ref_07a59b21" />
* 1.1 Supervised Learning Classical machine learning is often divided into two categories – Supervised and Unsupervised Learning.<ref name="ref_45cd" />
+
# The discipline of machine learning employs various approaches to teach computers to accomplish tasks where no fully satisfactory algorithm is available.<ref name="ref_07a59b21" />
* This type of machine learning involves algorithms that train on unlabeled data.<ref name="ref_9fd4">[https://searchenterpriseai.techtarget.com/definition/machine-learning-ML What is Machine learning (ML)?]</ref>
+
# Note: Unfortunately, as of April 2019 we no longer update non-English versions of Machine Learning Crash Course.<ref name="ref_c8219c15">[https://developers.google.com/machine-learning/glossary Machine Learning Glossary]</ref>
* This approach to machine learning involves a mix of the two preceding types.<ref name="ref_9fd4" />
+
# Bias (also known as the bias term) is referred to as b or w 0 in machine learning models.<ref name="ref_c8219c15" />
* Uses of machine learning Today, machine learning is used in a wide range of applications.<ref name="ref_9fd4" />
+
# A type of machine learning model for distinguishing among two or more discrete classes.<ref name="ref_c8219c15" />
* But just because some industries have seen benefits doesn't mean machine learning is without its downsides.<ref name="ref_9fd4" />
+
# Machine learning developers may inadvertently collect or label data in ways that influence an outcome supporting their existing beliefs.<ref name="ref_c8219c15" />
 +
# Machine learning at its most basic is the practice of using algorithms to parse data, learn from it, and then make a determination or prediction about something in the world.<ref name="ref_fad17c96">[https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial-intelligence-machine-learning-deep-learning-ai/ The Difference Between AI, Machine Learning, and Deep Learning?]</ref>
 +
# Machine learning came directly from minds of the early AI crowd, and the algorithmic approaches over the years included decision tree learning, inductive logic programming.<ref name="ref_fad17c96" />
 +
# As it turned out, one of the very best application areas for machine learning for many years was computer vision, though it still required a great deal of hand-coding to get the job done.<ref name="ref_fad17c96" />
 +
# Deep learning has enabled many practical applications of machine learning and by extension the overall field of AI.<ref name="ref_fad17c96" />
 +
# ML is one of the most exciting technologies that one would have ever come across.<ref name="ref_3ac7b374">[https://www.geeksforgeeks.org/machine-learning/ Machine Learning]</ref>
 +
# Machine learning is the concept that a computer program can learn and adapt to new data without human intervention.<ref name="ref_b8333047">[https://www.investopedia.com/terms/m/machine-learning.asp Machine Learning]</ref>
 +
# The various data applications of machine learning are formed through a complex algorithm or source code built into the machine or computer.<ref name="ref_b8333047" />
 +
# Machine learning is used in different sectors for various reasons.<ref name="ref_b8333047" />
 +
# Lending institutions can incorporate machine learning to predict bad loans and build a credit risk model.<ref name="ref_b8333047" />
 +
# A diverse community of developers, enterprises and researchers are using ML to solve challenging, real-world problems.<ref name="ref_1df90e27">[https://www.tensorflow.org/ TensorFlow]</ref>
 +
# Natural Language Derive insights from unstructured text using Google machine learning.<ref name="ref_f60c950c">[https://cloud.google.com/products/ai Google Cloud]</ref>
 +
# Translation Dynamically translate between languages using Google machine learning.<ref name="ref_f60c950c" />
 +
# At Emerj, the AI Research and Advisory Company, many of our enterprise clients feel as though they should be investing in machine learning projects, but they don’t have a strong grasp of what it is.<ref name="ref_03e6f181">[https://emerj.com/ai-glossary-terms/what-is-machine-learning/ What is Machine Learning?]</ref>
 +
# The above definition encapsulates the ideal objective or ultimate aim of machine learning, as expressed by many researchers in the field.<ref name="ref_03e6f181" />
 +
# The purpose of this article is to provide a business-minded reader with expert perspective on how machine learning is defined, and how it works.<ref name="ref_03e6f181" />
 +
# As with any concept, machine learning may have a slightly different definition, depending on whom you ask.<ref name="ref_03e6f181" />
 +
# Machine Learning is an international forum for research on computational approaches to learning.<ref name="ref_fec60db7">[https://www.springer.com/journal/10994 Machine Learning]</ref>
 +
# Rapidly build and deploy machine learning models using tools that meet your needs regardless of skill level.<ref name="ref_eb8d6df7">[https://azure.microsoft.com/en-us/services/machine-learning/ Azure Machine Learning]</ref>
 +
# Machine learning brings together computer science and statistics to harness that predictive power.<ref name="ref_20d2e3a8">[https://www.udacity.com/course/intro-to-machine-learning--ud120 Introduction to Machine Learning Course]</ref>
 +
# This is a class that will teach you the end-to-end process of investigating data through a machine learning lens.<ref name="ref_20d2e3a8" />
 +
# Machine learning could also be used for security applications, such as analysing email communications or internet usage.<ref name="ref_92e2dd00">[https://royalsociety.org/topics-policy/projects/machine-learning/videos-and-background-information/ What is machine learning?]</ref>
 +
# The project will focus on current and near-term (5-10 years) applications of machine learning.<ref name="ref_92e2dd00" />
 +
# Machine Learning can play a pivotal role in a range of applications such as Deep Learning, Reinforcement Learning, Natural Language Processing, etc.<ref name="ref_f8f1fce2">[https://www.edx.org/learn/machine-learning Learn Machine Learning with Online Courses and Classes]</ref>
 +
# Microsoft, Columbia, Caltech and other major universities and institutions offer introductory courses and tutorials in machine learning and artificial intelligence.<ref name="ref_f8f1fce2" />
 +
# Gain a stronger understanding of the major machine learning projects with helpful examples.<ref name="ref_f8f1fce2" />
 +
# Funding for research and development in the fields of machine learning and artificial intelligence is growing at a rapid pace.<ref name="ref_f8f1fce2" />
 +
# In machine learning terms, Billy invented regression – he predicted a value (price) based on known historical data.<ref name="ref_53a69c46">[https://vas3k.com/blog/machine_learning/ Machine Learning for Everyone]</ref>
 +
# Three components of machine learning Without all the AI-bullshit, the only goal of machine learning is to predict results based on incoming data.<ref name="ref_53a69c46" />
 +
# All ML tasks can be represented this way, or it's not an ML problem from the beginning.<ref name="ref_53a69c46" />
 +
# That's why selecting the right features usually takes way longer than all the other ML parts.<ref name="ref_53a69c46" />
 +
# The supply of able ML designers has yet to catch up to this demand.<ref name="ref_175ccf03">[https://www.toptal.com/machine-learning/machine-learning-theory-an-introductory-primer An Introduction to Machine Learning Theory and Its Applications: A Visual Tutorial with Examples]</ref>
 +
# Determining which inputs to use is an important part of ML design.<ref name="ref_175ccf03" />
 +
# We stick to simple problems in this post for the sake of illustration, but the reason ML exists is because, in the real world, the problems are much more complex.<ref name="ref_175ccf03" />
 +
# On this flat screen we can draw you a picture of, at most, a three-dimensional data set, but ML problems commonly deal with data with millions of dimensions, and very complex predictor functions.<ref name="ref_175ccf03" />
 +
# Machine learning is a subset of artificial intelligence (AI) in which algorithms learn by example from historical data to predict outcomes and uncover patterns not easily spotted by humans.<ref name="ref_ae9d3dc9">[https://www.datarobot.com/wiki/machine-learning/ DataRobot Artificial Intelligence Wiki]</ref>
 +
# For example, machine learning can reveal customers who are likely to churn, likely fraudulent insurance claims, and more.<ref name="ref_ae9d3dc9" />
 +
# Machine learning has practical implications across industry sectors, including healthcare, insurance, energy, marketing, manufacturing, financial technology (fintech), and more.<ref name="ref_ae9d3dc9" />
 +
# While most statistical analysis relies on rule-based decision-making, machine learning excels at tasks that are hard to define with exact step-by-step rules.<ref name="ref_ae9d3dc9" />
 +
# From Apple to Google to Toyota, companies across the world are pouring resources into developing AI systems with machine learning.<ref name="ref_c74f7a45">[https://www.techrepublic.com/article/machine-learning-the-smart-persons-guide/ Machine learning: A cheat sheet]</ref>
 +
# While there are different forms of AI, machine learning (ML) represents today's most widely valued mechanism for reaching intelligence.<ref name="ref_c74f7a45" />
 +
# What is machine learning?<ref name="ref_c74f7a45" />
 +
# Machine learning became popular in the 1990s, and returned to the public eye when Google's DeepMind beat the world champion of Go in 2016.<ref name="ref_c74f7a45" />
 +
# We will walk you step-by-step into the World of Machine Learning.<ref name="ref_2b67ef51">[https://www.udemy.com/course/machinelearning/ Machine Learning A-Z (Python & R in Data Science Course)]</ref>
 +
# This course is fun and exciting, but at the same time, we dive deep into Machine Learning.<ref name="ref_2b67ef51" />
 +
# Machine Learning is making the computer learn from studying data and statistics.<ref name="ref_f6cb7a50">[https://www.w3schools.com/python/python_ml_getting_started.asp Python Machine Learning]</ref>
 +
# In Machine Learning it is common to work with very large data sets.<ref name="ref_f6cb7a50" />
 +
# Create ML lets you quickly build and train Core ML models right on your Mac with no code.<ref name="ref_29ed2b55">[https://developer.apple.com/machine-learning/ Machine Learning]</ref>
 +
# The Journal of Machine Learning Research (JMLR) provides an international forum for the electronic and paper publication of high-quality scholarly articles in all areas of machine learning.<ref name="ref_4e9f9969">[https://www.jmlr.org/ Journal of Machine Learning Research]</ref>
 +
# -Support vector machines, or SVMs, is a machine learning algorithm for classification.<ref name="ref_56907392">[https://www.classcentral.com/course/machine-learning-835 Free Online Course: Machine Learning from Coursera]</ref>
 +
# Machine learning is speeding it up by orders of magnitude.<ref name="ref_34f7013d">[https://www.wired.com/tag/machine-learning/ Latest News, Photos & Videos]</ref>
 +
# For instance, if you provide a machine learning model with many songs that you enjoy, along with their corresponding audio statistics (dance-ability, instrumentality, tempo, or genre).<ref name="ref_343a899c">[https://towardsai.net/p/machine-learning/differences-between-ai-and-machine-learning-1255b182fc6 Machine Learning (ML) vs. Artificial Intelligence (AI) — Crucial Differences]</ref>
 +
# The machine learning model looks at each picture in the diverse dataset and finds common patterns found in pictures with labels with comparable indications.<ref name="ref_343a899c" />
 +
# Unsupervised learning, another type of machine learning, is the family of machine learning algorithms, which have main uses in pattern detection and descriptive modeling.<ref name="ref_343a899c" />
 +
# Machine learning can be dazzling, particularly its advanced sub-branches, i.e., deep learning and the various types of neural networks.<ref name="ref_343a899c" />
 +
# Perhaps the most popular data science methodologies come from machine learning.<ref name="ref_5ab14699">[https://online-learning.harvard.edu/course/data-science-machine-learning Data Science: Machine Learning]</ref>
 +
# What distinguishes machine learning from other computer guided decision processes is that it builds prediction algorithms using data.<ref name="ref_5ab14699" />
 
===소스===
 
===소스===
 
  <references />
 
  <references />
 +
 +
==메타데이터==
 +
===위키데이터===
 +
* ID :  [https://www.wikidata.org/wiki/Q2539 Q2539]
 +
===Spacy 패턴 목록===
 +
* [{'LOWER': 'machine'}, {'LEMMA': 'learning'}]
 +
* [{'LEMMA': 'ML'}]
 +
* [{'LOWER': 'statistical'}, {'LEMMA': 'learning'}]

2021년 2월 17일 (수) 01:39 기준 최신판

개요

  • 컴퓨터 과학의 핵심 과제 중 하나는 컴퓨터에게 수행 방법을 명시적으로 알려주지 않고 작업을 수행하도록 하는 것이다.
  • 많은 경우 작업은 매개변수가 있는 수학적 모델로 기술된다.
  • 이러한 모델의 매개변수는 통계적 방법을 사용하여 데이터에서 추정해야 한다.
  • 기계 학습이란 이 매개변수를 찾아가는 과정이라 할 수 있다.
  • fundamental problems in machine learning
    • regression
    • classification
    • 차원축소
    • probability density estimation
  • 기계 학습은 시스템에서 학습을 위해 사용하는 피드백의 특성에 따라 보통 다음의 세 가지 범주로 나누어진다:

관련된 항목들

노트

위키데이터

말뭉치

  1. If you are a newbie in machine learning you may have thought that what programming language should I learn?[1]
  2. Machine Learning is one of the fastest-growing fields which has witnessed an exponential growth in the technical world.[1]
  3. Python leads all the other languages with more than 60% of machine learning developers are using and prioritising it for development because python is easy to learn.[1]
  4. This programming language is the “Jack of all the trade” and continues to dominate over in the ML industry also.[1]
  5. Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.[2]
  6. Supervised machine learning algorithms can apply what has been learned in the past to new data using labeled examples to predict future events.[2]
  7. In contrast, unsupervised machine learning algorithms are used when the information used to train is neither classified nor labeled.[2]
  8. Reinforcement machine learning algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards.[2]
  9. To help those interested in the field better understand how to break into a career in machine learning, we compiled the most important details and resources.[3]
  10. In terms of specific positions, 94% of job postings that contained AI or machine learning terminology were for machine learning engineers, the report found.[3]
  11. "Software is eating the world and machine learning is eating software," Vitaly Gordon, vice president of data science and software engineering for Salesforce Einstein, told TechRepublic.[3]
  12. "Machine learning engineering is a discipline that requires production grade coding, PhD level machine learning, and the business acumen of a product manager.[3]
  13. So, can machine learning be self-taught?[4]
  14. Even though there are many different skills to learn in machine learning it is possible for you to self-teach yourself machine learning.[4]
  15. There are actually so many machine learning courses available now that choosing the right path for you can be quite daunting.[4]
  16. course is that it will give you the chance to see if machine learning is something that you are actually interested in.[4]
  17. which statuses you are reacting to—and using machine learning to make a highly educated guess about what you might want next.[5]
  18. Deep learning is machine learning on steroids: it uses a technique that gives machines an enhanced ability to find—and amplify—even the smallest patterns.[5]
  19. In machine learning, algorithms are 'trained' to find patterns and features in massive amounts of data in order to make decisions and predictions based on new data.[6]
  20. There are four basic steps for building a machine learning application (or model).[6]
  21. Training data is a data set representative of the data the machine learning model will ingest to solve the problem it’s designed to solve.[6]
  22. Supervised machine learning trains itself on a labeled data set.[6]
  23. Machine learning is a branch of artificial intelligence that includes methods, or algorithms, for automatically creating models from data.[7]
  24. Unlike a system that performs a task by following explicit rules, a machine learning system learns from experience.[7]
  25. We hear about applications of machine learning on a daily basis, although not all of them are unalloyed successes.[7]
  26. Game-playing machine learning is strongly successful for checkers, chess, shogi, and Go, having beaten human world champions.[7]
  27. Machine learning is one modern innovation that has helped man enhance not only many industrial and professional processes but also advances everyday living.[8]
  28. But what is machine learning?[8]
  29. Currently, machine learning has been used in multiple fields and industries.[8]
  30. The intelligent systems built on machine learning algorithms have the capability to learn from past experience or historical data.[8]
  31. Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so.[9]
  32. Types of machine learning Classical machine learning is often categorized by how an algorithm learns to become more accurate in its predictions.[9]
  33. this type of machine learning, data scientists supply algorithms with training data and define the variables they want the algorithm to assess for correlations.[9]
  34. This type of machine learning involves algorithms that train on unlabeled data.[9]
  35. Similar drag and drop modules have been added to Azure Machine Learning designer.[10]
  36. Scoring is also called prediction, and is the process of generating values based on a trained machine learning model, given some new input data.[10]
  37. Machine Learning Studio (classic) supports a flexible, customizable framework for machine learning.[10]
  38. In this phase of machine learning, you apply a trained model to new data, to generate predictions.[10]
  39. Some machine learning algorithms are described as “supervised” machine learning algorithms as they are designed for supervised machine learning problems.[11]
  40. Some machine learning algorithms do not just experience a fixed dataset.[11]
  41. Fitting a machine learning model is a process of induction.[11]
  42. In the context of machine learning, once we use induction to fit a model on a training dataset, the model can be used to make predictions.[11]
  43. A very important group of algorithms for both supervised and unsupervised machine learning are neural networks.[12]
  44. For instance, consider the example of using machine learning to recognize handwritten numbers between 0 and 9.[12]
  45. As the use of machine learning has taken off, so companies are now creating specialized hardware tailored to running and training machine-learning models.[12]
  46. In 2020, Google said its fourth-generation TPUs were 2.7 times faster than previous gen TPUs in MLPerf, a benchmark which measures how fast a system can carry out inference using a trained ML model.[12]
  47. 📚 Check out our editorial recommendations on the best machine learning books.[13]
  48. next → ← prev Applications of Machine learning Machine learning is a buzzword for today's technology, and it is growing very rapidly day by day.[14]
  49. We are using machine learning in our daily life even without knowing it such as Google Maps, Google assistant, Alexa, etc.[14]
  50. Below are some most trending real-world applications of Machine Learning: 1.[14]
  51. While using Google, we get an option of "Search by voice," it comes under speech recognition, and it's a popular application of machine learning.[14]
  52. A subset of machine learning is closely related to computational statistics, which focuses on making predictions using computers; but not all machine learning is statistical learning.[15]
  53. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning.[15]
  54. Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so.[15]
  55. The discipline of machine learning employs various approaches to teach computers to accomplish tasks where no fully satisfactory algorithm is available.[15]
  56. Note: Unfortunately, as of April 2019 we no longer update non-English versions of Machine Learning Crash Course.[16]
  57. Bias (also known as the bias term) is referred to as b or w 0 in machine learning models.[16]
  58. A type of machine learning model for distinguishing among two or more discrete classes.[16]
  59. Machine learning developers may inadvertently collect or label data in ways that influence an outcome supporting their existing beliefs.[16]
  60. Machine learning at its most basic is the practice of using algorithms to parse data, learn from it, and then make a determination or prediction about something in the world.[17]
  61. Machine learning came directly from minds of the early AI crowd, and the algorithmic approaches over the years included decision tree learning, inductive logic programming.[17]
  62. As it turned out, one of the very best application areas for machine learning for many years was computer vision, though it still required a great deal of hand-coding to get the job done.[17]
  63. Deep learning has enabled many practical applications of machine learning and by extension the overall field of AI.[17]
  64. ML is one of the most exciting technologies that one would have ever come across.[18]
  65. Machine learning is the concept that a computer program can learn and adapt to new data without human intervention.[19]
  66. The various data applications of machine learning are formed through a complex algorithm or source code built into the machine or computer.[19]
  67. Machine learning is used in different sectors for various reasons.[19]
  68. Lending institutions can incorporate machine learning to predict bad loans and build a credit risk model.[19]
  69. A diverse community of developers, enterprises and researchers are using ML to solve challenging, real-world problems.[20]
  70. Natural Language Derive insights from unstructured text using Google machine learning.[21]
  71. Translation Dynamically translate between languages using Google machine learning.[21]
  72. At Emerj, the AI Research and Advisory Company, many of our enterprise clients feel as though they should be investing in machine learning projects, but they don’t have a strong grasp of what it is.[22]
  73. The above definition encapsulates the ideal objective or ultimate aim of machine learning, as expressed by many researchers in the field.[22]
  74. The purpose of this article is to provide a business-minded reader with expert perspective on how machine learning is defined, and how it works.[22]
  75. As with any concept, machine learning may have a slightly different definition, depending on whom you ask.[22]
  76. Machine Learning is an international forum for research on computational approaches to learning.[23]
  77. Rapidly build and deploy machine learning models using tools that meet your needs regardless of skill level.[24]
  78. Machine learning brings together computer science and statistics to harness that predictive power.[25]
  79. This is a class that will teach you the end-to-end process of investigating data through a machine learning lens.[25]
  80. Machine learning could also be used for security applications, such as analysing email communications or internet usage.[26]
  81. The project will focus on current and near-term (5-10 years) applications of machine learning.[26]
  82. Machine Learning can play a pivotal role in a range of applications such as Deep Learning, Reinforcement Learning, Natural Language Processing, etc.[27]
  83. Microsoft, Columbia, Caltech and other major universities and institutions offer introductory courses and tutorials in machine learning and artificial intelligence.[27]
  84. Gain a stronger understanding of the major machine learning projects with helpful examples.[27]
  85. Funding for research and development in the fields of machine learning and artificial intelligence is growing at a rapid pace.[27]
  86. In machine learning terms, Billy invented regression – he predicted a value (price) based on known historical data.[28]
  87. Three components of machine learning Without all the AI-bullshit, the only goal of machine learning is to predict results based on incoming data.[28]
  88. All ML tasks can be represented this way, or it's not an ML problem from the beginning.[28]
  89. That's why selecting the right features usually takes way longer than all the other ML parts.[28]
  90. The supply of able ML designers has yet to catch up to this demand.[29]
  91. Determining which inputs to use is an important part of ML design.[29]
  92. We stick to simple problems in this post for the sake of illustration, but the reason ML exists is because, in the real world, the problems are much more complex.[29]
  93. On this flat screen we can draw you a picture of, at most, a three-dimensional data set, but ML problems commonly deal with data with millions of dimensions, and very complex predictor functions.[29]
  94. Machine learning is a subset of artificial intelligence (AI) in which algorithms learn by example from historical data to predict outcomes and uncover patterns not easily spotted by humans.[30]
  95. For example, machine learning can reveal customers who are likely to churn, likely fraudulent insurance claims, and more.[30]
  96. Machine learning has practical implications across industry sectors, including healthcare, insurance, energy, marketing, manufacturing, financial technology (fintech), and more.[30]
  97. While most statistical analysis relies on rule-based decision-making, machine learning excels at tasks that are hard to define with exact step-by-step rules.[30]
  98. From Apple to Google to Toyota, companies across the world are pouring resources into developing AI systems with machine learning.[31]
  99. While there are different forms of AI, machine learning (ML) represents today's most widely valued mechanism for reaching intelligence.[31]
  100. What is machine learning?[31]
  101. Machine learning became popular in the 1990s, and returned to the public eye when Google's DeepMind beat the world champion of Go in 2016.[31]
  102. We will walk you step-by-step into the World of Machine Learning.[32]
  103. This course is fun and exciting, but at the same time, we dive deep into Machine Learning.[32]
  104. Machine Learning is making the computer learn from studying data and statistics.[33]
  105. In Machine Learning it is common to work with very large data sets.[33]
  106. Create ML lets you quickly build and train Core ML models right on your Mac with no code.[34]
  107. The Journal of Machine Learning Research (JMLR) provides an international forum for the electronic and paper publication of high-quality scholarly articles in all areas of machine learning.[35]
  108. -Support vector machines, or SVMs, is a machine learning algorithm for classification.[36]
  109. Machine learning is speeding it up by orders of magnitude.[37]
  110. For instance, if you provide a machine learning model with many songs that you enjoy, along with their corresponding audio statistics (dance-ability, instrumentality, tempo, or genre).[38]
  111. The machine learning model looks at each picture in the diverse dataset and finds common patterns found in pictures with labels with comparable indications.[38]
  112. Unsupervised learning, another type of machine learning, is the family of machine learning algorithms, which have main uses in pattern detection and descriptive modeling.[38]
  113. Machine learning can be dazzling, particularly its advanced sub-branches, i.e., deep learning and the various types of neural networks.[38]
  114. Perhaps the most popular data science methodologies come from machine learning.[39]
  115. What distinguishes machine learning from other computer guided decision processes is that it builds prediction algorithms using data.[39]

소스

  1. 이동: 1.0 1.1 1.2 1.3 Top 5 Programming Languages and their Libraries for Machine Learning in 2020
  2. 이동: 2.0 2.1 2.2 2.3 What is Machine Learning? A definition - Expert System
  3. 이동: 3.0 3.1 3.2 3.3 How to become a machine learning engineer: A cheat sheet
  4. 이동: 4.0 4.1 4.2 4.3 Can machine learning be self-taught?
  5. 이동: 5.0 5.1 What is machine learning?
  6. 이동: 6.0 6.1 6.2 6.3 What is Machine Learning?
  7. 이동: 7.0 7.1 7.2 7.3 What is machine learning? Intelligence derived from data
  8. 이동: 8.0 8.1 8.2 8.3 Top 10 real-life examples of Machine Learning
  9. 이동: 9.0 9.1 9.2 9.3 What is Machine learning (ML)?
  10. 이동: 10.0 10.1 10.2 10.3 ML Studio (classic): Machine Learning Scoring - Azure
  11. 이동: 11.0 11.1 11.2 11.3 14 Different Types of Learning in Machine Learning
  12. 이동: 12.0 12.1 12.2 12.3 What is machine learning? Everything you need to know
  13. Best Masters Programs in Machine Learning (ML) for 2020
  14. 이동: 14.0 14.1 14.2 14.3 Applications of Machine learning
  15. 이동: 15.0 15.1 15.2 15.3 Machine learning
  16. 이동: 16.0 16.1 16.2 16.3 Machine Learning Glossary
  17. 이동: 17.0 17.1 17.2 17.3 The Difference Between AI, Machine Learning, and Deep Learning?
  18. Machine Learning
  19. 이동: 19.0 19.1 19.2 19.3 Machine Learning
  20. TensorFlow
  21. 이동: 21.0 21.1 Google Cloud
  22. 이동: 22.0 22.1 22.2 22.3 What is Machine Learning?
  23. Machine Learning
  24. Azure Machine Learning
  25. 이동: 25.0 25.1 Introduction to Machine Learning Course
  26. 이동: 26.0 26.1 What is machine learning?
  27. 이동: 27.0 27.1 27.2 27.3 Learn Machine Learning with Online Courses and Classes
  28. 이동: 28.0 28.1 28.2 28.3 Machine Learning for Everyone
  29. 이동: 29.0 29.1 29.2 29.3 An Introduction to Machine Learning Theory and Its Applications: A Visual Tutorial with Examples
  30. 이동: 30.0 30.1 30.2 30.3 DataRobot Artificial Intelligence Wiki
  31. 이동: 31.0 31.1 31.2 31.3 Machine learning: A cheat sheet
  32. 이동: 32.0 32.1 Machine Learning A-Z (Python & R in Data Science Course)
  33. 이동: 33.0 33.1 Python Machine Learning
  34. Machine Learning
  35. Journal of Machine Learning Research
  36. Free Online Course: Machine Learning from Coursera
  37. Latest News, Photos & Videos
  38. 이동: 38.0 38.1 38.2 38.3 Machine Learning (ML) vs. Artificial Intelligence (AI) — Crucial Differences
  39. 이동: 39.0 39.1 Data Science: Machine Learning

메타데이터

위키데이터

Spacy 패턴 목록

  • [{'LOWER': 'machine'}, {'LEMMA': 'learning'}]
  • [{'LEMMA': 'ML'}]
  • [{'LOWER': 'statistical'}, {'LEMMA': 'learning'}]