Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. Tensor-Flow uses dataflow graphs to represent computation, shared state, and the operations that mutate that state. It maps the nodes of a dataflow graph across many machines in a cluster, and within a machine across multiple computational devices, including multicore CPUs, general-purpose GPUs, and custom-designed ASICs known as Tensor Processing Units (TPUs). This architecture gives flexibility to the application developer: whereas in previous "parameter server" designs the management of shared state is built into the system, TensorFlow enables developers to experiment with novel optimizations and training algorithms. TensorFlow supports a variety of applications, with a focus on training and inference on deep neural networks. Several Google services use TensorFlow in production, we have released it as an open-source project, and it has become widely used for machine learning research. In this paper, we describe the TensorFlow dataflow model and demonstrate the compelling performance that TensorFlow achieves for several real-world applications.

/pdf/tensorflow-a-system-for-large-scale-machine-learning-10wgdjhl6k.pdf

TensorFlow: a system for large-scale machine learning

TensorFlow is an interface for expressing machine learning algorithms, and an
implementation for executing such algorithms. A computation expressed using
TensorFlow can be executed with little or no change on a wide variety of
heterogeneous systems, ranging from mobile devices such as phones and tablets
up to large-scale distributed systems of hundreds of machines and thousands of
computational devices such as GPU cards. The system is flexible and can be used
to express a wide variety of algorithms, including training and inference
algorithms for deep neural network models, and it has been used for conducting
research and for deploying machine learning systems into production across more
than a dozen areas of computer science and other fields, including speech
recognition, computer vision, robotics, information retrieval, natural language
processing, geographic information extraction, and computational drug
discovery. This paper describes the TensorFlow interface and an implementation
of that interface that we have built at Google. The TensorFlow API and a
reference implementation were released as an open-source package under the
Apache 2.0 license in November, 2015 and are available at www.tensorflow.org.

/pdf/tensorflow-large-scale-machine-learning-on-heterogeneous-2yk4fgchw6.pdf

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. The book is written in an informal, accessible style, complete with pseudo-code for the most important algorithms. All topics are copiously illustrated with color images and worked examples drawn from such application domains as biology, text processing, computer vision, and robotics. Rather than providing a cookbook of different heuristic methods, the book stresses a principled model-based approach, often using the language of graphical models to specify models in a concise and intuitive way. Almost all the models described have been implemented in a MATLAB software package--PMTK (probabilistic modeling toolkit)--that is freely available online. The book is suitable for upper-level undergraduates with an introductory-level college math background and beginning graduate students.

Machine Learning : A Probabilistic Perspective

Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very high variance such as to perfectly model the training data. Unfortunately, many application domains do not have access to big data, such as medical image analysis. This survey focuses on Data Augmentation, a data-space solution to the problem of limited data. Data Augmentation encompasses a suite of techniques that enhance the size and quality of training datasets such that better Deep Learning models can be built using them. The image augmentation algorithms discussed in this survey include geometric transformations, color space augmentations, kernel filters, mixing images, random erasing, feature space augmentation, adversarial training, generative adversarial networks, neural style transfer, and meta-learning. The application of augmentation methods based on GANs are heavily covered in this survey. In addition to augmentation techniques, this paper will briefly discuss other characteristics of Data Augmentation such as test-time augmentation, resolution impact, final dataset size, and curriculum learning. This survey will present existing methods for Data Augmentation, promising developments, and meta-level decisions for implementing Data Augmentation. Readers will understand how Data Augmentation can improve the performance of their models and expand limited datasets to take advantage of the capabilities of big data.

/pdf/a-survey-on-image-data-augmentation-for-deep-learning-4ru1bj2hbb.pdf

A survey on Image Data Augmentation for Deep Learning

Large deep neural network models have recently demonstrated state-of-the-art accuracy on hard visual recognition tasks. Unfortunately such models are extremely time consuming to train and require large amount of compute cycles. We describe the design and implementation of a distributed system called Adam comprised of commodity server machines to train such models that exhibits world-class performance, scaling and task accuracy on visual recognition tasks. Adam achieves high efficiency and scalability through whole system co-design that optimizes and balances workload computation and communication. We exploit asynchrony throughout the system to improve performance and show that it additionally improves the accuracy of trained models. Adam is significantly more efficient and scalable than was previously thought possible and used 30x fewer machines to train a large 2 billion connection model to 2x higher accuracy in comparable time on the ImageNet 22,000 category image classification task than the system that previously held the record for this benchmark. We also show that task accuracy improves with larger models. Our results provide compelling evidence that a distributed systems-driven approach to deep learning using current training algorithms is worth pursuing.

/pdf/project-adam-building-an-efficient-and-scalable-deep-mz26kixwji.pdf

Project Adam: building an efficient and scalable deep learning training system

Techniques are disclosed for creating, modifying, categorizing, modeling, distributing, purchasing, selling, and otherwise using themes and theme-related information. Themes can represent various types of contextual aspects or situations, and can model high-level concepts of activities or states not reflected in individual contextual attributes that each model a single aspect of the state of a user, their computing device, the surrounding physical environment, and/or the current cyber-environment. Such themes specify inter-relationships among a set of contextual attributes, and can have associated theme-related information such as theme-specific attributes, theme layouts used to present information and functionality, CSes that provide theme attribute values, and CCs that process theme information. Disclosed techniques can identify one or more themes that currently match the modeled context, select one of the matching themes as a current theme, and provide an appropriate response (e.g., by presenting appropriate information and/or providing appropriate functionality) based on the current theme.

Thematic response to a computer user's context, such as by a wearable personal computer

The present invention relates to a system and methodology to facilitate collaboration and communications between entities such as between automated applications, parties to a communication and/or combinations thereof. The systems and methods of the present invention include a service that supports collaboration and communication by learning predictive models that provide forecasts of one or more aspects of a users' presence and availability. Presence forecasts include a user's current or future locations at different levels of location precision and usage of different devices or applications. Availability assessments include inferences about the cost of interrupting a user in different ways and a user's current or future access to one or more communication channels. The predictive models are constructed from data collected by considering user activity and proximity from multiple devices, in addition to analysis of the content of users' calendars, the time of day, and day of week, for example. Various applications are provided that employ the presence and availability information supplied by the models in order to facilitate collaboration and communications between entities.

Methods and architecture for cross-device activity monitoring, reasoning, and visualization for providing status and forecasts of a users' presence and availability

A system and method is provided to facilitate communication and collaboration by considering the timing of a user's activities on one or more clients via accessing, from a centralized server, information about the user's client-server interactions. The systems and methods can harness existing protocols and data exchange used in legacy client-server applications for email, making available to one or more client-side message routing applications, information about a user's interactions with email across multiple clients. Applications include considering the time since the last client-server interaction to guide decisions about if, when, and how to route messages so as to limit the mobile relay of information a user has already seen, providing information to colleagues about a user's current or past “inbox presence,” and forecasting the time until a user will have access to a device or communication channel.

Harnessing information about the timing of a user's client-server interactions to enhance messaging and collaboration services

We present methods for inferring the cost of interrupting users based on multiple streams of events including information generated by interactions with computing devices, visual and acoustical analyses, and data drawn from online calendars. Following a review of prior work on techniques for deliberating about the cost of interruption associated with notifications, we introduce methods for learning models from data that can be used to compute the expected cost of interruption for a user. We describe the Interruption Workbench, a set of event-capture and modeling tools. Finally, we review experiments that characterize the accuracy of the models for predicting interruption cost and discuss research directions.

/pdf/learning-and-reasoning-about-interruption-39luy7bzvs.pdf

Johnson T. Apacible

Papers

Project Adam: building an efficient and scalable deep learning training system

Thematic response to a computer user's context, such as by a wearable personal computer

Methods and architecture for cross-device activity monitoring, reasoning, and visualization for providing status and forecasts of a users' presence and availability

Harnessing information about the timing of a user's client-server interactions to enhance messaging and collaboration services

Learning and reasoning about interruption