No abstract

Suppose you are given some data set drawn from an underlying probability distribution P and you want to estimate a "simple" subset S of input space such that the probability that a test point drawn from P lies outside of S equals some a priori specified value between 0 and 1. We propose a method to approach this problem by trying to estimate a function f that is positive on S and negative on the complement. The functional form of f is given by a kernel expansion in terms of a potentially small subset of the training data; it is regularized by controlling the length of the weight vector in an associated feature space. The expansion coefficients are found by solving a quadratic programming problem, which we do by carrying out sequential optimization over pairs of input patterns. We also provide a theoretical analysis of the statistical performance of our algorithm. The algorithm is a natural extension of the support vector algorithm to the case of unlabeled data.

My first exposure to Support Vector Machines came this spring when heard Sue Dumais present impressive results on text categorization using this analysis technique. This issue's collection of essays should help familiarize our readers with this interesting new racehorse in the Machine Learning stable. Bernhard Scholkopf, in an introductory overview, points out that a particular advantage of SVMs over other learning algorithms is that it can be analyzed theoretically using concepts from computational learning theory, and at the same time can achieve good performance when applied to real problems. Examples of these real-world applications are provided by Sue Dumais, who describes the aforementioned text-categorization problem, yielding the best results to date on the Reuters collection, and Edgar Osuna, who presents strong results on application to face detection. Our fourth author, John Platt, gives us a practical guide and a new technique for implementing the algorithm efficiently

Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods that are used in the literature and in industry. This paper describes a set of concrete best practices that document analysis researchers can use to get good results with neural networks. The most important practice is getting a training set as large as possible: we expand the training set by adding a new form of distorted data. The next most important practice is that convolutional neural networks are better suited for visual document tasks than fully connected networks. We propose that a simple "do-it-yourself" implementation of convolution with a flexible architecture is suitable for many visual document problems. This simple convolutional neural network does not require complex methods, such as momentum, weight decay, structuredependent learning rates, averaging layers, tangent prop, or even finely-tuning the architecture. The end result is a very simple yet general architecture which can yield state-of-the-art performance for document analysis. We illustrate our claims on the MNIST set of English digit images.

The theory of elasticity describes deformable materials such as rubber, cloth, paper, and flexible metals. We employ elasticity theory to construct differential equations that model the behavior of non-rigid curves, surfaces, and solids as a function of time. Elastically deformable models are active: they respond in a natural way to applied forces, constraints, ambient media, and impenetrable obstacles. The models are fundamentally dynamic and realistic animation is created by numerically solving their underlying differential equations. Thus, the description of shape and the description of motion are unified.

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to train visual detectors for words that commonly occur in captions, including many different parts of speech such as nouns, verbs, and adjectives. The word detector outputs serve as conditional inputs to a maximum-entropy language model. The language model learns from a set of over 400,000 image descriptions to capture the statistics of word usage. We capture global semantics by re-ranking caption candidates using sentence-level features and a deep multimodal similarity model. Our system is state-of-the-art on the official Microsoft COCO benchmark, producing a BLEU-4 score of 29.1%. When human judges compare the system captions to ones written by other people on our heldout test set, the system captions have equal or better quality 34% of the time.

Text categorization -the assignment of natural language texts to one or more predefined categories based on their content -is an important component in many information organization and management tasks. We compare the effectiveness of five different automatic learning algorithms for text categorization in terms of learning speed, realtime classification speed, and classification accuracy. We also examine training set size, and alternative document representations. Very accurate text classifiers can be learned automatically from training examples. Linear Support Vector Machines (SVMs) are particularly promising because they are very accurate, quick to train, and quick to evaluate.

We have created a network that allocates a new computational unit whenever an unusual pattern is presented to the network. This network forms compact representations, yet learns easily and rapidly. The network can be used at any time in the learning process and the learning patterns do not have to be repeated. The units in this network respond to only a local region of the space of input values.The network learns by allocating new units and adjusting the parameters of existing units. If the network performs poorly on a presented pattern, then a new unit is allocated which corrects the response to the presented pattern. If the network performs well on a presented pattern, then the network parameters are updated using standard LMS gradient descent.We have obtained good results with our resource-allocating network (RAN). For predicting the Mackey Glass chaotic time series, our network learns much faster than do those using backpropagation and uses a comparable number of synapses.