WorldCat Identities

MASSACHUSETTS INST OF TECH CAMBRIDGE MA CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING

Overview
Works: 17 works in 17 publications in 1 language and 17 library holdings
Publication Timeline
.
Most widely held works by MASSACHUSETTS INST OF TECH CAMBRIDGE MA CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING
Stability Results in Learning Theory( )

1 edition published in 2005 in English and held by 0 WorldCat member libraries worldwide

The problem of proving generalization bounds for the performance of learning algorithms can be formulated as a problem of bounding the bias and variance of estimators of the expected error. We show how various stability assumptions can be employed for this purpose. We provide a necessary and sufficient stability condition for bounding the bias and variance for the Empirical Risk Minimization algorithm, and various sufficient conditions for bounding bias and variance of estimators for general algorithms. We discuss settings in which it is possible to obtain exponential bounds, and we prove an extension of the bounded-difference inequality for "almost always" stable algorithms
On the Role of Object-Specific Features for Real World Object Recognition in Biological Vision( )

1 edition published in 2006 in English and held by 0 WorldCat member libraries worldwide

Models of object recognition in cortex have so far been mostly applied to tasks involving the recognition of isolated objects presented on blank backgrounds. However, ultimately models of the visual system have to prove themselves in real world object recognition tasks. Here we took a first step in this direction: We investigated the performance of the HMAX model of object recognition in cortex recently presented by Riesenhuber & Poggio on the task of face detection using natural images. We found that the standard version of HMAX performs rather poorly on this task, due to the low specificity of the hardwired feature set of C2 units in the model (corresponding to neurons in intermediate visual area V4) that do not show any particular tuning for faces vs. background. We show how visual features of intermediate complexity can be learned in HMAX using a simple learning rule. Using this rule, HMAX outperforms a classical machine vision face detection system presented in the literature. This suggests an important role for the set of features in intermediate visual areas in object recognition
Regularization Through Feature Knock Out( )

1 edition published in 2004 in English and held by 0 WorldCat member libraries worldwide

In this paper, we present and analyze a novel regularization technique based on enhancing our dataset with corrupted copies of the original data. The motivation is that since the learning algorithm lacks information about which parts of the data are reliable, it has to produce more robust classification functions. We then demonstrate how this regularization leads to redundancy in the resulting classifiers, which is somewhat in contrast to the common interpretations of the Occam's razor principle. Using this framework, we propose a simple addition to the gentle boosting algorithm which enables it to work with only a few examples. We test this new algorithm on a variety of datasets and show convincing results
Shape Representation in V4: Investigating Position-Specific Tuning for Boundary Confirmation with the Standard Model of Object Recognition( )

1 edition published in 2004 in English and held by 0 WorldCat member libraries worldwide

The computational processes in the intermediate stages of the ventral pathway responsible for visual object recognition are not well understood. A recent physiological study by A. Pasupathy and C. Connor in intermediate area V4 using contour stimuli, proposes that a population of V4 neurons display object-centered, position-specific curvature tuning. The standard model of object recognition, a recently developed model to account for recognition properties of IT cells (extending classical suggestions by Hubel, Wiesel and others), is used here to model the response of the V4 cells described in Pasupathy and Connor. Our results show that a feedforward, network level mechanism can exhibit selectivity and invariance properties that correspond to the responses of the V4 cells. These results suggest how object-centered, position-specific curvature tuning of V4 cells may arise from combinations of complex V1 cell responses. Furthermore, the model makes predictions about the responses of the same V4 cells studied by Pasupathy and Connor to novel gray level patterns, such as gratings and natural images. These predictions suggest specific experiments to further explore shape representation in V4
People Recognition in Image Sequences by Supervised Learning( )

1 edition published in 2000 in English and held by 0 WorldCat member libraries worldwide

We describe a system that learns from examples to recognize people in images taken indoors. Images of people are represented by color-based and shape-based features. Recognition is carried out through combinations of Support Vector Machine classi- ers (SVMs). Di erent types of multiclass strategies based on SVMs are explored and compared to k-Nearest Neighbors classi ers (kNNs). The system works in real time and shows high performance rates for people recognition throughout one day
Perception Strategies in Hierarchical Vision Systems( )

1 edition published in 2006 in English and held by 0 WorldCat member libraries worldwide

Flat appearance-based systems, which combine clever image representations with standard classifiers, might be the most effective way to recognize objects using current technologies. In the future, however, it seems probable that hierarchical representations might have better performance. In such systems, the image representation consists of a sequence of sets of features, where each subsequent set is computed based on the previous sets. The main contributions of this paper are to: (1) pose the question what is the best way to employ discriminative methods for hierarchical image representations? ; (2) enumerate some of the alternative hierarchies while drawing connections to recent work by brain researchers; (3) study experimentally the different alternatives. As we will show, the strategy used can make a substantial difference
A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex( )

1 edition published in 2005 in English and held by 0 WorldCat member libraries worldwide

We describe a quantitative theory to account for the computations performed by the feedforward path of the ventral stream of visual cortex and the local circuits implementing them. We show that a model instantiating the theory is capable of performing recognition on datasets of complex images at the level of human observers in rapid categorization tasks. We also show that the theory is consistent with (and in some case has predicted) several properties of neurons in V1, V4, IT and PFC. The theory seems sufficiently comprehensive, detailed and satisfactory to represent an interesting challenge for physiologists and modelers: either disprove its basic features or propose alternative theories of equivalent scope. The theory suggests a number of open questions for visual physiology and psychophysics
Component-Based Face Detection( )

1 edition published in 2001 in English and held by 0 WorldCat member libraries worldwide

We present a component-based, trainable system for detecting frontal and near-frontal views of faces in still gray images. The system consists of a two-level hierarchy of Support Vector Machine (SVM) classifiers. On the first level, component classifiers independently detect components of a face. On the second level, a single classifier checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face. We propose a method for automatically learning components by using 3-D head models. This approach has the advantage that no manual interaction is required for choosing and extracting components. Experiments show that the component-based system is significantly more robust against rotations in depth than a comparable system trained on whole face patterns
Feature Reduction and Hierarchy of Classifiers for Fast Object Detection in Video Images( )

1 edition published in 2001 in English and held by 0 WorldCat member libraries worldwide

We present a two-step method to speed-up object detection systems in computer vision that use Support Vector Machines (SVMs) as classifiers. In a first step we perform feature reduction by choosing relevant image features according to a measure derived from statistical learning theory. In a second step we build a hierarchy of classifiers. On the bottom level, a simple and fast classifier analyzes the whole image and rejects large parts of the background. On the top level, a slower but more accurate classifier performs the final detection. Experiments with a face detection system show that combining feature reduction with hierarchical classification leads to a speed-up by a factor of 170 with similar classification performance. criterion of the classification algorithm to select the optimal feature subset. Wrapper methods can provide more accurate solutions than filter methods [5], but in general are more computationally expensive. We present a new wrapper method to reduce the dimensions of both input and feature space of an SVM. An alternative approach for speeding-up SVM classification has been proposed in [7] by reducing the number of support vectors. Feature reduction is a generic tool that can be applied to any classification problem. When dealing with a specific classification task we can use prior knowledge about the type of data to speed-up classification
Neural Mechanisms of Object Recognition( )

1 edition published in 2002 in English and held by 0 WorldCat member libraries worldwide

Single-unit recordings from behaving monkeys and human functional magnetic resonance imaging studies have continued to provide a host of experimental data on the properties and mechanisms of object recognition in cortex. Recent advances in object recognition, spanning issues regarding invariance, selectivity, representation and levels of recognition have allowed us to propose a putative model of object recognition in cortex
General Mechanism for Tuning: Gain Control Circuits and Synapses Underlie Tuning of Cortical Neurons( )

1 edition published in 2004 in English and held by 0 WorldCat member libraries worldwide

Tuning to an optimal stimulus is a widespread property of neurons in cortex. We propose that such tuning is a consequence of normalization or gain control circuits. We also present a biologically plausible neural circuitry of tuning
Biophysical Models of Neural Computation: Max and Tuning Circuits( )

1 edition published in 2007 in English and held by 0 WorldCat member libraries worldwide

Pooling under a softmax operation and Gaussian-like tuning in the form of a normalized dotproduct were proposed as the key operations in a recent model of object recognition in the ventral stream of visual cortex. We investigate how these two operations might be implemented by plausible circuits of a few hundred neurons in cortex. We consider two di erent sets of circuits whose di erent properties may correspond to the conditions in visual and barrel cortices, respectively. They constitute a plausibility proof that stringent timing and accuracy constraints imposed by the neuroscience of object recognition can be satisfied with standard spiking and synaptic mechanisms. We provide simulations illustrating the performance of the circuits, and discuss the relevance of our work to neurophysiology as well as what bearing it may have on the search for maximum and tuning circuits in cortex
Robust Boosting for Learning from Few Examples( )

1 edition published in 2006 in English and held by 0 WorldCat member libraries worldwide

The authors present and analyze a novel regularization technique based on enhancing their data set with corrupted copies of their original data. The motivation is that since the learning algorithm lacks information about which parts of the data are reliable, it has to make more robust classification functions. Using this framework, they propose a simple addition to the gentle boosting algorithm that enables it to work with only a few examples. They test this new algorithm on a variety of data sets and show convincing results
Face Recognition with Support Vector Machines: Global versus Component-Based Approach( )

1 edition published in 2001 in English and held by 0 WorldCat member libraries worldwide

We present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. In the component system we first locate facial components, extract them and combine them into a single feature vector which is classified by a Support Vector Machine (SVM). The two global systems recognize faces by classifying a single feature vector consisting of the gray values of the whole face image. In the first global system we trained a single SVM classifier for each person in the database. The second system consists of sets of viewpoint-specific SVM classifiers and involves clustering during training. We performed extensive tests on a database which included faces rotated up to about 40 deg in depth. The component system clearly outperformed both global systems on all tests
Face Detection in Still Gray Images( )

1 edition published in 2000 in English and held by 0 WorldCat member libraries worldwide

We present a trainable system for detecting frontal and near-frontal views of faces in still gray images using Support Vector Machines (SVMs). We first consider the problem of detecting the whole face pattern by a single SVM classifier. In this context we compare different types of image features, present and evaluate a new method for reducing the number features and discuss practical issues concerning the parameterization of SVMs and the selection of training data. The second part of the paper describes a component-based method for face detection consisting of a two-level hierarchy of SVM classifiers. On the first level, component classifiers independently detect components of a face, such as the eyes, the nose, and the mouth. On the second level, a single classifier checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face
On Stability and Concentration of Measure( )

1 edition published in 2004 in English and held by 0 WorldCat member libraries worldwide

Stability conditions can be thought of as a way of controlling the variance of the learning process. Strong stability conditions additionally imply concentration of certain quantities around their expected values. It was shown recently that stability of learning algorithms is closely related to their generalization and consistency. In this paper we examine stability conditions from this point of view
Ultra-FDst Object Recognition from Few Spikes( )

1 edition published in 2005 in English and held by 0 WorldCat member libraries worldwide

Understanding the complex brain computations leading to object recognition requires quantitatively characterizing the information represented in inferior temporal cortex (IT), the highest stage of the primate visual stream. A read-out technique based on a trainable classifier is used to characterize the neural coding of selectivity and invariance at the population level. The activity of very small populations of independently recorded IT neurons (~100 randomly selected cells) over very short time intervals (as small as 12.5 ms) contains surprisingly accurate and robust information about both object "identity" and "category", which is furthermore highly invariant to object position and scale. Significantly, selectivity and invariance are present even for novel objects, indicating that these properties arise from the intrinsic circuitry and do not require object-specific learning. Within the limits of the technique, there is no detectable difference in the latency or temporal resolution of the IT information supporting so-called categorization (a.k. basic level) and identification (a.k. subordinate level) tasks. Furthermore, where information, in particular information about stimulus location and scale, can also be readout from the same small population of IT neurons. These results show how it is possible to decode invariant object information rapidly, accurately and robustly from a small population in IT and provide insights into the nature of the neural code for different kinds of object-related information
 
moreShow More Titles
fewerShow Fewer Titles
Languages
English (17)