We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

/pdf/imagenet-classification-with-deep-convolutional-neural-1190x9a6b9.pdf

ImageNet Classification with Deep Convolutional Neural Networks

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Gradient-based learning applied to document recognition

LIBSVM is a library for Support Vector Machines (SVMs). We have been actively developing this package since the year 2000. The goal is to help users to easily apply SVM to their applications. LIBSVM has gained wide popularity in machine learning and many other areas. In this article, we present all implementation details of LIBSVM. Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.

/pdf/libsvm-a-library-for-support-vector-machines-2gdxasg9zv.pdf

LIBSVM: A library for support vector machines

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

Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.

/pdf/dropout-a-simple-way-to-prevent-neural-networks-from-4gtr92okhv.pdf

Dropout: a simple way to prevent neural networks from overfitting

A saltating sample image enhancement system and method that provides an image processing operation in which a filter considers one or one or more exact source image pixels; one or more bilinearly interpolated source image samples, where the bilinear weights are coupled to the position of the target pixel relative to the source pixels; and (optionally) one or more linearly interpolated source image samples, where the linear weights are coupled to the position of the target pixel relative to the source pixels. The filter can construct a spatially continuous image statistic.

Image processing using saltating samples

Audio fingerprinting is a powerful tool for identifying either streaming or file-based audio, using a database of fingerprints. This paper presents two new applications: duplicate detection, whose goal is to identify duplicate audio clips in a set, even if they differ in compression quality or duration, and thumbnail generation, which aims at providing a representative short clip of a music track. Each application is self-contained in that it does not require an external database of fingerprints. Thanks to the robustness of the fingerprinting engine, both applications perform well.

/pdf/duplicate-detection-and-audio-thumbnails-with-audio-1wyczvch2m.pdf

Duplicate Detection and Audio Thumbnails with Audio Fingerprinting

This technical report introduces Trill – a new query processor for analytics. Trill fulfills a combination of three requirements for a query processor to serve the diverse big data analytics space: (1) Query Model: Trill is based on a tempo-relational model that enables it to handle streaming and relational queries with early results, across the latency spectrum from real-time to offline; (2) Fabric and Language Integration: Trill is architected as a high-level language library that supports rich data-types and user libraries, and integrates well with existing distribution fabrics and applications; and (3) Performance: Trill’s throughput is high across the latency spectrum. For streaming data, Trill’s throughput is 2-4 orders of magnitude higher than today’s comparable streaming engines. For offline relational queries, Trill’s throughput is comparable to a major modern commercial columnar DBMS. Trill uses a streaming batched-columnar data representation with a new dynamic compilation-based system architecture that addresses all these requirements. In this technical report, we describe Trill’s new design and architecture, and report experimental results that demonstrate Trill’s high performance across diverse analytics scenarios. We also describe how Trill’s ability to support diverse analytics has resulted in its adoption across many usage scenarios at Microsoft.

/pdf/the-trill-incremental-analytics-engine-2a61lcqqru.pdf

The Trill Incremental Analytics Engine

Temporal dynamics of information content carried by neurons in the primary visual cortex

This paper develops a particular error correction code which can be effectively decoded by a relatively simple neural network. In high noise situations, this code is comparable to that used at present in deep space communications. The neural decoder has N! stable states with only N2 neurons, and can quickly extract information from analog noise. This example illustrates the effectiveness of neural networks in solving real problems when the problem can be cast in such a fashion that it fits gracefully on the network.

John Platt

Papers

Image processing using saltating samples

Duplicate Detection and Audio Thumbnails with Audio Fingerprinting

The Trill Incremental Analytics Engine

Temporal dynamics of information content carried by neurons in the primary visual cortex

Analog decoding using neural networks