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

Graph matching is a fundamental problem in Computer Vision and Machine Learning We present two contributions First, we give a new spectral relaxation technique for approximate solutions to matching problems, that naturally incorporates one-to-one or one-to-many constraints within the relaxation scheme The second is a normalization procedure for existing graph matching scoring functions that can dramatically improve the matching accuracy It is based on a reinterpretation of the graph matching compatibility matrix as a bipartite graph on edges for which we seek a bistochastic normalization We evaluate our two contributions on a comprehensive test set of random graph matching problems, as well as on image correspondence problem Our normalization procedure can be used to improve the performance of many existing graph matching algorithms, including spectral matching, graduated assignment and semidefinite programming

Balanced Graph Matching

Described is a technology by which a user pastes selected data into a command line of a program, including when the selected data is non-textual. Upon detecting the paste (or drop) action, a variable name is automatically generated and inserted at the current point in a command line, where it acts as a proxy for the pasted data itself. A data structure comprising the selected data or transformed data corresponding to that selected data is maintained in program storage, e.g., RAM allocated to the program. In one aspect, a handler may be used to transform the data from one format into another that may be used by a particular program. For example, text may be reformatted into an array on which the program operates. The handler may be selected from a plurality of possible handlers, including customized handlers.

Pasting Various Data into a Programming Environment

A data broker observes datasets that are opened or created by a user. The data broker looks for related datasets in a data catalog. If a related dataset is found, the data broker asks the user if they want to access the related dataset. If the user is interested, then the data broker asks the data owner if they are willing to share access to the related dataset with the user. The data owner may deny access, allow access, or request the user's identity. If the user does not want to provide his or her identity, then access to the related dataset is denied. If the user does provide his or her identity, then the data owner determines whether or not to share the data with that user. Once the owner approves sharing the related dataset, then the dataset or a link to the dataset is sent to the user.

Brokered Exchange of Private Data

In this paper we introduce and experiment with a framework for learning local perceptual distance functions for visual recognition. We learn a distance function for each training image as a combination of elementary distances between patch-based visual features. We apply these combined local distance functions to the tasks of image retrieval and classification of novel images. On the Caltech 101 object recognition benchmark, we achieve 60.3% mean recognition across classes using 15 training images per class, which is better than the best published performance by Zhang, et al.

Image Retrieval and Classification Using Local Distance Functions

Everyday inductive reasoning draws on many kinds of knowledge, including knowledge about relationships between properties and knowledge about relationships between objects Previous accounts of inductive reasoning generally focus on just one kind of knowledge: models of causal reasoning often focus on relationships between properties, and models of similarity-based reasoning often focus on similarity relationships between objects We present a Bayesian model of inductive reasoning that incorporates both kinds of knowledge, and show that it accounts well for human inferences about the properties of biological species

John Platt

Papers

Balanced Graph Matching

Pasting Various Data into a Programming Environment

Brokered Exchange of Private Data

Image Retrieval and Classification Using Local Distance Functions

Combining causal and similarity-based reasoning