# 딥 러닝

(Deep learning에서 넘어옴)

둘러보기로 가기
검색하러 가기
## introduction

- Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems.
- image classification and labeling
- face recognition
- gesture recognition
- video search and analytics
- speech recognition and translation
- recommendation engines
- indexing and search

## memo

- Kristinn R. Thórisson, Jordi Bieger, Thröstur Thorarensen, Jóna S. Sigurðardóttir, Bas R. Steunebrink, Why Artificial Intelligence Needs a Task Theory --- And What It Might Look Like, arXiv:1604.04660 [cs.AI], April 15 2016, http://arxiv.org/abs/1604.04660

## 노트

- This article explains deep learning vs. machine learning and how they fit into the broader category of artificial intelligence.
^{[1]} - Deep learning is a subset of machine learning that's based on artificial neural networks.
^{[1]} - Now that you have the overview of machine learning vs. deep learning, let's compare the two techniques.
^{[1]} - For this reason, deep learning is rapidly transforming many industries, including healthcare, energy, finance, and transportation.
^{[1]} - Finally, Kelleher considers the future of deep learning—major trends, possible developments, and significant challenges.
^{[2]} - Today, deep learning enables farmers to deploy equipment that can see and differentiate between crop plants and weeds.
^{[3]} - For example, deep learning can be as effective as a dermatologist in classifying skin cancers, if not more so.
^{[3]} - Deep learning is based on representation learning.
^{[4]} - Deep learning doesn’t rely on human expertise as much as traditional machine learning.
^{[4]} - DL allows us to make discoveries in data even when the developers are not sure what they are trying to find.
^{[4]} - All major commercial speech recognition systems (like Microsoft Cortana, Alexa, Google Assistant, Apple Siri) are based on deep learning.
^{[4]} - Getting started in deep learning – and adopting an organized, sustainable, and reproducible workflow – can be challenging.
^{[5]} - In the field of deep learning, there continues to be a deluge of research and new papers published daily.
^{[5]} - NLP and deep learning continue to advance, nearly on a daily basis.
^{[5]} - Natural language processing has made incredible advances through advanced techniques in deep learning.
^{[5]} - Let's begin to learn what is Deep Learning, and its various aspects.
^{[6]} - Deep learning can be considered as a subset of machine learning.
^{[6]} - Deep learning has aided image classification, language translation, speech recognition.
^{[6]} - Artificial neural networks, comprising many layers, drive deep learning.
^{[6]} - The clearest explanation of deep learning I have come across...
^{[7]} - About the book Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library.
^{[7]} - Deep learning is one of the most influential and fastest growing fields in artificial intelligence.
^{[8]} - Deep learning is an important element of data science, which includes statistics and predictive modeling.
^{[9]} - At its simplest, deep learning can be thought of as a way to automate predictive analytics.
^{[9]} - To understand deep learning, imagine a toddler whose first word is dog.
^{[9]} - As a result, deep learning may sometimes be referred to as deep neural learning or deep neural networking.
^{[9]} - Course material loosely follows the organization of the text: I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, 2016.
^{[10]} - Deep learning is making a big impact across industries.
^{[11]} - Businesses often outsource the development of deep learning.
^{[11]} - You can get started with deep learning for free with IBM Watson Studio and Watson Machine Learning.
^{[11]} - You’ll then delve deeper and apply Deep Learning by building models and algorithms using libraries like Keras, PyTorch, and Tensorflow.
^{[12]} - The number of publications addressing deep learning as applied to medical imaging techniques is a small fraction of this number.
^{[13]} - Novel denoising algorithms based on deep learning have been studied intensively and showed impressive potential (29).
^{[13]} - Using a combination of q-Space deep learning and of simultaneous multi-slice imaging, Golkov et al.
^{[13]} - Manjón and Coupe (59) used two-stage strategy with deep learning for noise reduction.
^{[13]} - This course was developed by the TensorFlow team and Udacity as a practical approach to deep learning for software developers.
^{[14]} - In most discussions, deep learning means using deep neural networks.
^{[15]} - I mentioned that deep learning is a form of machine learning.
^{[15]} - There are many examples of problems that currently require deep learning to produce the best models.
^{[15]} - As I mentioned earlier, most deep learning is done with deep neural networks.
^{[15]} - For example, deep learning is used to classify images, recognize speech, detect objects and describe content.
^{[16]} - And those differences should be known—examples of machine learning and deep learning are everywhere.
^{[17]} - More specifically, deep learning is considered an evolution of machine learning.
^{[17]} - And as deep learning becomes more refined, we’ll see even more advanced applications of artificial intelligence in customer service.
^{[17]} - That’s a widely shared sentiment among AI practitioners, any of whom can easily rattle off a long list of deep learning’s drawbacks.
^{[18]} - Until the past year or so, he says, “there had been a feeling that deep learning was magic.
^{[18]} - “So I have a hard time imagining that deep learning will go away at this point,” Cox says.
^{[18]} - Unfortunately, neither of these milestones solved the fundamental problems of deep learning.
^{[18]} - Automated Driving: Automotive researchers are using deep learning to automatically detect objects such as stop signs and traffic lights.
^{[19]} - Cancer researchers are using deep learning to automatically detect cancer cells.
^{[19]} - Deep learning is being used in automated hearing and speech translation.
^{[19]} - Deep learning is commonly used across apps in computer vision, conversational AI and recommendation systems.
^{[20]} - Computer vision apps use deep learning to gain knowledge from digital images and videos.
^{[20]} - In early talks on deep learning, Andrew described deep learning in the context of traditional artificial neural networks.
^{[21]} - Finally, he is clear to point out that the benefits from deep learning that we are seeing in practice come from supervised learning.
^{[21]} - When you hear the term deep learning, just think of a large deep neural net.
^{[21]} - He describes deep learning in terms of the algorithms ability to discover and learn good representations using feature learning.
^{[21]} - The adjective "deep" in deep learning comes from the use of multiple layers in the network.
^{[22]} - In deep learning, each level learns to transform its input data into a slightly more abstract and composite representation.
^{[22]} - The word "deep" in "deep learning" refers to the number of layers through which the data is transformed.
^{[22]} - Advances in hardware have driven renewed interest in deep learning.
^{[22]} - Deep learning is used across all industries for a number of different tasks.
^{[23]}

### 소스

- ↑
^{1.0}^{1.1}^{1.2}^{1.3}Deep learning vs. machine learning - Azure Machine Learning - ↑ Deep Learning
- ↑
^{3.0}^{3.1}What Is Deep Learning? - How It Works - ↑
^{4.0}^{4.1}^{4.2}^{4.3}A Guide to Deep Learning and Neural Networks - ↑
^{5.0}^{5.1}^{5.2}^{5.3}Deep Learning - ↑
^{6.0}^{6.1}^{6.2}^{6.3}What is Deep Learning and How Does It Works? - ↑
^{7.0}^{7.1}Deep Learning with Python - ↑ What is Deep Learning?
- ↑
^{9.0}^{9.1}^{9.2}^{9.3}What is Deep Learning and How Does it Work? - ↑ Deep Learning
- ↑
^{11.0}^{11.1}^{11.2}Deep Learning - Neural Networks and Deep Learning - ↑ Deep Learning Professional Certificate
- ↑
^{13.0}^{13.1}^{13.2}^{13.3}Applications of Deep Learning to Neuro-Imaging Techniques - ↑ Intro to TensorFlow for Deep Learning
- ↑
^{15.0}^{15.1}^{15.2}^{15.3}What is deep learning? Algorithms that mimic the human brain - ↑ What is deep learning?
- ↑
^{17.0}^{17.1}^{17.2}Deep learning vs machine learning - ↑
^{18.0}^{18.1}^{18.2}^{18.3}News Feature: What are the limits of deep learning? - ↑
^{19.0}^{19.1}^{19.2}What Is Deep Learning? - ↑
^{20.0}^{20.1}Deep Learning - ↑
^{21.0}^{21.1}^{21.2}^{21.3}What is Deep Learning? - ↑
^{22.0}^{22.1}^{22.2}^{22.3}Deep learning - ↑ Deep Learning Definition