This book is aimed to provide an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas are chosen with the following three criteria: 1) expertise or knowledge of the authors; 2) the application areas that have already been transformed by the successful use of deep learning technology, such as speech recognition and computer vision; and 3) the application areas that have the potential to be impacted significantly by deep learning and that have gained concentrated research efforts, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.
In Chapter 1, we provide the background of deep learning, as intrinsically connected to the use of multiple layers of nonlinear transformations to derive features from the sensory signals such as speech and visual images. In the most recent literature, deep learning is embodied also as representation learning, which involves a hierarchy of features or concepts where higher-level representations of them are defined from lower-level ones and where the same lower-level representations help to define higher-level ones. In Chapter 2, a brief historical account of deep learning is presented. In particular, selected chronological development of speech recognition is used to illustrate the recent impact of deep learning that has become a dominant technology in speech recognition industry within only a few years since the start of a collaboration between academic and industrial researchers in applying deep learning to speech recognition. In Chapter 3, a three-way classification scheme for a large body of work in deep learning is developed. We classify a growing number of deep learning techniques into unsupervised, supervised, and hybrid categories, and present qualitative descriptions and a literature survey for each category. From Chapter 4 to Chapter 6, we discuss in detail three popular deep networks and related learning methods, one in each category. Chapter 4 is devoted to deep autoencoders as a prominent example of the unsupervised deep learning techniques. Chapter 5 gives a major example in the hybrid deep network category, which is the discriminative feed-forward neural network for supervised learning with many layers initialized using layer-by-layer generative, unsupervised pre-training. In Chapter 6, deep stacking networks and several of the variants are discussed in detail, which exemplify the discriminative or supervised deep learning techniques in the three-way categorization scheme.
Apr 20, 2019 MIT Deep Learning Book (beautiful and flawless PDF version) MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville. If this repository helps you in anyway, show your love ️ by putting a ⭐️ on this project ️ Deep Learning.
In Chapters 7-11, we select a set of typical and successful applications of deep learning in diverse areas of signal and information processing and of applied artificial intelligence. In Chapter 7, we review the applications of deep learning to speech and audio processing, with emphasis on speech recognition organized according to several prominent themes. In Chapters 8, we present recent results of applying deep learning to language modeling and natural language processing. Chapter 9 is devoted to selected applications of deep learning to information retrieval including Web search. In Chapter 10, we cover selected applications of deep learning to image object recognition in computer vision. Selected applications of deep learning to multi-modal processing and multi-task learning are reviewed in Chapter 11. Finally, an epilogue is given in Chapter 12 to summarize what we presented in earlier chapters and to discuss future challenges and directions.
With huge strides in AI—from advances in the driverless vehicle realm, to mastering games such as poker and Go, to automating customer service interactions—this advanced technology is poised to revolutionize businesses. But the terms AI, machine learning, and deep learning are often used haphazardly and interchangeably, when there are key differences between each type of technology. Here's a guide to the differences between these three tools to help you master machine intelligence.
SURVEY: Take this artificial intelligence and machine learning survey, and get free copy of the research report
Artificial Intelligence (AI)
AI is the broadest way to think about advanced, computer intelligence. In 1956 at the Dartmouth Artificial Intelligence Conference, the technology was described as such: 'Every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it.'
AI can refer to anything from a computer program playing a game of chess, to a voice-recognition system like Amazon's Alexa interpreting and responding to speech. The technology can broadly be categorized into three groups: Narrow AI, artificial general intelligence (AGI), and superintelligent AI.
IBM's Deep Blue, which beat chess grand master Garry Kasparov at the game in 1996, or Google DeepMind's AlphaGo, which in 2016 beat Lee Sedol at Go, are examples of narrow AI—AI that is skilled at one specific task. This is different from artificial general intelligence (AGI), which is AI that is considered human-level, and can perform a range of tasks.
Superintelligent AI takes things a step further. As Nick Bostrom describes it, this is 'an intellect that is much smarter than the best human brains in practically every field, including scientific creativity, general wisdom and social skills.' In other words, it's when the machines have outsmarted us.
SEE: Sensor'd enterprise: IoT, ML, and big data (ZDNet special report) | Download the report as a PDF (TechRepublic)
Machine Learning (ML)
Machine learning is one subfield of AI. The core principle here is that machines take data and 'learn' for themselves. It's currently the most promising tool in the AI kit for businesses. ML systems can quickly apply knowledge and training from large data sets to excel at facial recognition, speech recognition, object recognition, translation, and many other tasks. Unlike hand-coding a software program with specific instructions to complete a task, ML allows a system to learn to recognize patterns on its own and make predictions.
While Deep Blue and DeepMind are both types of AI, Deep Blue was rule-based, dependent on programming—so it was not a form of ML. DeepMind, on the other hand, is: It beat the world champion in Go by training itself on a large data set of expert moves.
Is your business interested in integrating machine learning into its strategy? Amazon, Baidu, Google, IBM, Microsoft and others offer machine learning platforms that businesses can use.
Deep Learning
Deep learning is a subset of ML. It uses some ML techniques to solve real-world problems by tapping into neural networks that simulate human decision-making. Deep learning can be expensive, and requires massive datasets to train itself on. That's because there are a huge number of parameters that need to be understood by a learning algorithm, which can initially produce a lot of false-positives. For instance, a deep learning algorithm could be instructed to 'learn' what a cat looks like. It would take a very massive data set of images for it to understand the very minor details that distinguish a cat from, say, a cheetah or a panther or a fox.
More about artificial intelligence
As mentioned above, in March 2016, a major AI victory was achieved when DeepMind's AlphaGo program beat world champion Lee Sedol in 4 out of 5 games of Go using deep learning. The way the deep learning system worked was by combining 'Monte-Carlo tree search with deep neural networks that have been trained by supervised learning, from human expert games, and by reinforcement learning from games of self-play,' according to Google.
Deep learning also has business applications. It can take a huge amount of data—millions of images, for example—and recognize certain characteristics. Text-based searches, fraud detection, spam detection, handwriting recognition, image search, speech recognition, Street View detection, and translation are all tasks that can be performed through deep learning. At Google, deep learning networks have replaced many 'handcrafted rule-based systems,' for instance.
SEE: Machine learning: The smart person's guide (TechRepublic)
Deep learning is also highly susceptible to bias. When Google's facial recognition system was initially rolled out, for instance, it tagged many black faces as gorillas. 'That's an example of what happens if you have no African American faces in your training set,' said Anu Tewary, chief data officer for Mint at Intuit. 'If you have no African Americans working on the product. If you have no African Americans testing the product. When your technology encounters African American faces, it's not going to know how to behave.'
Some also believe that deep learning is overhyped. Sundown AI, for instance, has mastered automated customer interactions using a combination of ML and policy graph algorithms—not deep learning.
Next Big Thing Newsletter
Be in the know about smart cities, AI, Internet of Things, VR, autonomous driving, drones, robotics, and more of the coolest tech innovations. Delivered Wednesdays and Fridays
Sign up today Sign up todayAlso see...
- The 6 most exciting AI advances of 2016 (TechRepublic)
- 3 major AI trends to watch in 2017 (TechRepublic)
- Microsoft's new breakthrough: AI that's as good as humans at listening... on the phone (ZDNet)
- Five ways your company can get started implementing AI and ML (ZDNet)
- Research: 63% say business will benefit from AI (Tech Pro Research)
- How Google's DeepMind beat the game of Go, which is even more complex than chess (TechRepublic)
- Smart machines are about to run the world: Here's how to prepare (TechRepublic)
- Why AI could destroy more jobs than it creates, and how to save them (TechRepublic)
- 7 trends for artificial intelligence in 2016: 'Like 2015 on steroids' (TechRepublic)