기계 학습

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:
  • 지도 학습
  • 비지도 학습
  • 강화 학습

관련된 항목들

• 인공지능
• 회귀와 분류
• 선형 회귀
• 로지스틱 회귀
• 나이브 베이즈 분류
• 마르코프 체인
• 마르코프 연쇄 몬테카를로 방법
• 은닉 마르코프 모델
• 칼만 필터
• 베이즈 네트워크
• K 근접 이웃
• 결정 트리
• 랜덤 포레스트
• 서포트 벡터 머신
• K-평균 알고리즘
• Kernel regression
• Gaussian mixture model
• Radial basis function
• DBSCAN
• 토픽 모델링
• 주성분 분석
• 특이값 분해
• Latent semantic analysis
• 잠재 디리클레 할당
• TF-IDF
• EM 알고리즘
• 유전 프로그래밍
• Symbolic regression
• 그래프 모형
• 쿨백-라이블러 발산
• 활성화 함수
• ReLU
• 퍼셉트론
• ADALINE
• 경사 하강법
• 확률적 경사 하강법
• 오차역전파법
• 손실 함수
• Pooling
• Vanishing gradient problem
• 딥 러닝
• 인공 신경망
• 합성곱 신경망
• 순환 인공 신경망
• Long Short-Term Memory
• Gated recurrent unit
• Autoencoder
• 생성적 적대 신경망
• Deep Q-Network
• LeNet-5
• AlexNet
• VGGNet
• GoogLeNet
• BERT
• Residual neural network
• Differentiable neural computer
• 자연어 처리
• 컴퓨터 비전
• OpenCV
• 영상 처리
• 지도 학습
• 비지도 학습
• 강화 학습
• 광학 문자 인식
• 음성 인식
• 음성 합성
• 이미지 분류
• 객체 인식
• 안면 인식 시스템
• 동작 인식
• 기계 번역
• 추천 시스템
• 협업 필터링
• 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

위키데이터

• ID : Q2539

말뭉치

1. If you are a newbie in machine learning you may have thought that what programming language should I learn?
2. Machine Learning is one of the fastest-growing fields which has witnessed an exponential growth in the technical world.
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.
4. This programming language is the “Jack of all the trade” and continues to dominate over in the ML industry also.
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.
6. Supervised machine learning algorithms can apply what has been learned in the past to new data using labeled examples to predict future events.
7. In contrast, unsupervised machine learning algorithms are used when the information used to train is neither classified nor labeled.
8. Reinforcement machine learning algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards.
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.
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.
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.
12. "Machine learning engineering is a discipline that requires production grade coding, PhD level machine learning, and the business acumen of a product manager.
13. So, can machine learning be self-taught?
14. Even though there are many different skills to learn in machine learning it is possible for you to self-teach yourself machine learning.
15. There are actually so many machine learning courses available now that choosing the right path for you can be quite daunting.
16. course is that it will give you the chance to see if machine learning is something that you are actually interested in.
17. which statuses you are reacting to—and using machine learning to make a highly educated guess about what you might want next.
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.
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.
20. There are four basic steps for building a machine learning application (or model).
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.
22. Supervised machine learning trains itself on a labeled data set.
23. Machine learning is a branch of artificial intelligence that includes methods, or algorithms, for automatically creating models from data.
24. Unlike a system that performs a task by following explicit rules, a machine learning system learns from experience.
25. We hear about applications of machine learning on a daily basis, although not all of them are unalloyed successes.
26. Game-playing machine learning is strongly successful for checkers, chess, shogi, and Go, having beaten human world champions.
27. Machine learning is one modern innovation that has helped man enhance not only many industrial and professional processes but also advances everyday living.
28. But what is machine learning?
29. Currently, machine learning has been used in multiple fields and industries.
30. The intelligent systems built on machine learning algorithms have the capability to learn from past experience or historical data.
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.
32. Types of machine learning Classical machine learning is often categorized by how an algorithm learns to become more accurate in its predictions.
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.
34. This type of machine learning involves algorithms that train on unlabeled data.
35. Similar drag and drop modules have been added to Azure Machine Learning designer.
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.
37. Machine Learning Studio (classic) supports a flexible, customizable framework for machine learning.
38. In this phase of machine learning, you apply a trained model to new data, to generate predictions.
39. Some machine learning algorithms are described as “supervised” machine learning algorithms as they are designed for supervised machine learning problems.
40. Some machine learning algorithms do not just experience a fixed dataset.
41. Fitting a machine learning model is a process of induction.
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.
43. A very important group of algorithms for both supervised and unsupervised machine learning are neural networks.
44. For instance, consider the example of using machine learning to recognize handwritten numbers between 0 and 9.
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.
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.
47. 📚 Check out our editorial recommendations on the best machine learning books.
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.
49. We are using machine learning in our daily life even without knowing it such as Google Maps, Google assistant, Alexa, etc.
50. Below are some most trending real-world applications of Machine Learning: 1.
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.
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.
53. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning.
54. Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so.
55. The discipline of machine learning employs various approaches to teach computers to accomplish tasks where no fully satisfactory algorithm is available.
56. Note: Unfortunately, as of April 2019 we no longer update non-English versions of Machine Learning Crash Course.
57. Bias (also known as the bias term) is referred to as b or w 0 in machine learning models.
58. A type of machine learning model for distinguishing among two or more discrete classes.
59. Machine learning developers may inadvertently collect or label data in ways that influence an outcome supporting their existing beliefs.
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.
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.
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.
63. Deep learning has enabled many practical applications of machine learning and by extension the overall field of AI.
64. ML is one of the most exciting technologies that one would have ever come across.
65. Machine learning is the concept that a computer program can learn and adapt to new data without human intervention.
66. The various data applications of machine learning are formed through a complex algorithm or source code built into the machine or computer.
67. Machine learning is used in different sectors for various reasons.
68. Lending institutions can incorporate machine learning to predict bad loans and build a credit risk model.
69. A diverse community of developers, enterprises and researchers are using ML to solve challenging, real-world problems.
70. Natural Language Derive insights from unstructured text using Google machine learning.
71. Translation Dynamically translate between languages using Google machine learning.
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.
73. The above definition encapsulates the ideal objective or ultimate aim of machine learning, as expressed by many researchers in the field.
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.
75. As with any concept, machine learning may have a slightly different definition, depending on whom you ask.
76. Machine Learning is an international forum for research on computational approaches to learning.
77. Rapidly build and deploy machine learning models using tools that meet your needs regardless of skill level.
78. Machine learning brings together computer science and statistics to harness that predictive power.
79. This is a class that will teach you the end-to-end process of investigating data through a machine learning lens.
80. Machine learning could also be used for security applications, such as analysing email communications or internet usage.
81. The project will focus on current and near-term (5-10 years) applications of machine learning.
82. Machine Learning can play a pivotal role in a range of applications such as Deep Learning, Reinforcement Learning, Natural Language Processing, etc.
83. Microsoft, Columbia, Caltech and other major universities and institutions offer introductory courses and tutorials in machine learning and artificial intelligence.
84. Gain a stronger understanding of the major machine learning projects with helpful examples.
85. Funding for research and development in the fields of machine learning and artificial intelligence is growing at a rapid pace.
86. In machine learning terms, Billy invented regression – he predicted a value (price) based on known historical data.
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.
88. All ML tasks can be represented this way, or it's not an ML problem from the beginning.
89. That's why selecting the right features usually takes way longer than all the other ML parts.
90. The supply of able ML designers has yet to catch up to this demand.
91. Determining which inputs to use is an important part of ML design.
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.
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.
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.
95. For example, machine learning can reveal customers who are likely to churn, likely fraudulent insurance claims, and more.
96. Machine learning has practical implications across industry sectors, including healthcare, insurance, energy, marketing, manufacturing, financial technology (fintech), and more.
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.
98. From Apple to Google to Toyota, companies across the world are pouring resources into developing AI systems with machine learning.
99. While there are different forms of AI, machine learning (ML) represents today's most widely valued mechanism for reaching intelligence.
100. What is machine learning?
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.
102. We will walk you step-by-step into the World of Machine Learning.
103. This course is fun and exciting, but at the same time, we dive deep into Machine Learning.
104. Machine Learning is making the computer learn from studying data and statistics.
105. In Machine Learning it is common to work with very large data sets.
106. Create ML lets you quickly build and train Core ML models right on your Mac with no code.
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.
108. -Support vector machines, or SVMs, is a machine learning algorithm for classification.
109. Machine learning is speeding it up by orders of magnitude.
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).
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.
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.
113. Machine learning can be dazzling, particularly its advanced sub-branches, i.e., deep learning and the various types of neural networks.
114. Perhaps the most popular data science methodologies come from machine learning.
115. What distinguishes machine learning from other computer guided decision processes is that it builds prediction algorithms using data.