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

There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms - such as mobile phones, embedded devices, and accelerators (e.g., FPGAs, ASICs) - requires significant manual effort. We propose TVM, a compiler that exposes graph-level and operator-level optimizations to provide performance portability to deep learning workloads across diverse hardware back-ends. TVM solves optimization challenges specific to deep learning, such as high-level operator fusion, mapping to arbitrary hardware primitives, and memory latency hiding. It also automates optimization of low-level programs to hardware characteristics by employing a novel, learning-based cost modeling method for rapid exploration of code optimizations. Experimental results show that TVM delivers performance across hardware back-ends that are competitive with state-of-the-art, hand-tuned libraries for low-power CPU, mobile GPU, and server-class GPUs. We also demonstrate TVM's ability to target new accelerator back-ends, such as the FPGA-based generic deep learning accelerator. The system is open sourced and in production use inside several major companies.

/pdf/tvm-an-automated-end-to-end-optimizing-compiler-for-deep-33mpz38jk4.pdf

TVM: an automated end-to-end optimizing compiler for deep learning

The artificial neural network (ANN)-a machine learning technique inspired by the human neuronal synapse system-was introduced in the 1950s. However, the ANN was previously limited in its ability to solve actual problems, due to the vanishing gradient and overfitting problems with training of deep architecture, lack of computing power, and primarily the absence of sufficient data to train the computer system. Interest in this concept has lately resurfaced, due to the availability of big data, enhanced computing power with the current graphics processing units, and novel algorithms to train the deep neural network. Recent studies on this technology suggest its potentially to perform better than humans in some visual and auditory recognition tasks, which may portend its applications in medicine and healthcare, especially in medical imaging, in the foreseeable future. This review article offers perspectives on the history, development, and applications of deep learning technology, particularly regarding its applications in medical imaging.

/pdf/deep-learning-in-medical-imaging-general-overview-12w9xmam40.pdf

Deep Learning in Medical Imaging: General Overview.

The field of machine learning is witnessing its golden era as deep learning slowly becomes the leader in this domain. Deep learning uses multiple layers to represent the abstractions of data to build computational models. Some key enabler deep learning algorithms such as generative adversarial networks, convolutional neural networks, and model transfers have completely changed our perception of information processing. However, there exists an aperture of understanding behind this tremendously fast-paced domain, because it was never previously represented from a multiscope perspective. The lack of core understanding renders these powerful methods as black-box machines that inhibit development at a fundamental level. Moreover, deep learning has repeatedly been perceived as a silver bullet to all stumbling blocks in machine learning, which is far from the truth. This article presents a comprehensive review of historical and recent state-of-the-art approaches in visual, audio, and text processing; social network analysis; and natural language processing, followed by the in-depth analysis on pivoting and groundbreaking advances in deep learning applications. It was also undertaken to review the issues faced in deep learning such as unsupervised learning, black-box models, and online learning and to illustrate how these challenges can be transformed into prolific future research avenues.

A Survey on Deep Learning: Algorithms, Techniques, and Applications

We propose a novel deep learning training criterion, named permutation invariant training (PIT), for speaker independent multi-talker speech separation, commonly known as the cocktail-party problem. Different from the multi-class regression technique and the deep clustering (DPCL) technique, our novel approach minimizes the separation error directly. This strategy effectively solves the long-lasting label permutation problem, that has prevented progress on deep learning based techniques for speech separation. We evaluated PIT on the WSJ0 and Danish mixed-speech separation tasks and found that it compares favorably to non-negative matrix factorization (NMF), computational auditory scene analysis (CASA), and DPCL and generalizes well over unseen speakers and languages. Since PIT is simple to implement and can be easily integrated and combined with other advanced techniques, we believe improvements built upon PIT can eventually solve the cocktail-party problem.

Permutation invariant training of deep models for speaker-independent multi-talker speech separation

We introduce computational network (CN), a unified framework for describing arbitrary learning machines, such as deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short term memory (LSTM), logistic regression, and maximum entropy model, that can be illustrated as a series of computational steps. A CN is a directed graph in which each leaf node represents an input value or a parameter and each non-leaf node represents a matrix operation upon its children. We describe algorithms to carry out forward computation and gradient calculation in CN and introduce most popular computation node types used in a typical CN. We further introduce the computational network toolkit (CNTK), an implementation of CN that supports both GPU and CPU. We describe the architecture and the key components of the CNTK, the command line options to use CNTK, and the network definition and model editing language, and provide sample setups for acoustic model, language model, and spoken language understanding. We also describe the Argon speech recognition decoder as an example to integrate with CNTK.

/pdf/an-introduction-to-computational-networks-and-the-2kabqb9yg3.pdf

An Introduction to Computational Networks and the Computational Network Toolkit

A system includes acquisition of meeting data associated with a meeting, determination of a plurality of meeting participants based on the acquired meeting data, acquisition of e-mail data associated with each of the plurality of meeting participants, generation of a meeting language model based on the acquired e-mail data and the meeting data, and transcription of audio associated with the meeting based on the meeting language model.

Meeting-adapted language model for speech recognition

A system includes acquisition of a domain grammar, determination of an interpolated grammar based on the domain grammar and a base grammar, determination of a delta domain grammar based on an augmented first grammar and the interpolated grammar, determination of an out-of-vocabulary class based on the domain grammar and the base grammar, insertion of the out-of-vocabulary class into a composed transducer composed of the augmented first grammar and one or more other transducers to generate an updated composed transducer, composition of the delta domain grammar and the updated composed transducer, and application of the composition of the delta domain grammar and the updated composed transducer to an output of an acoustic model.

Christopher H. Basoglu

Papers

An Introduction to Computational Networks and the Computational Network Toolkit

Meeting-adapted language model for speech recognition

Online language model interpolation for automatic speech recognition