Browsing CBCL Memos (1993 - 2004) by Subject "Artificial Intelligence"
Now showing items 1-20 of 22
-
Active Learning with Statistical Models
(1995-03-21)For many types of learners one can compute the statistically 'optimal' way to select data. We review how these techniques have been used with feedforward neural networks. We then show how the same principles may be ... -
Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifiers
(1996-12-01)The Support Vector (SV) machine is a novel type of learning machine, based on statistical learning theory, which contains polynomial classifiers, neural networks, and radial basis function (RBF) networks as special ... -
Cooperative Physics of Fly Swarms: An Emergent Behavior
(1995-04-11)We have simulated the behavior of several artificial flies, interacting visually with each other. Each fly is described by a simple tracking system (Poggio and Reichardt, 1973; Land and Collett, 1974) which summarizes ... -
Factorial Hidden Markov Models
(1996-02-09)We present a framework for learning in hidden Markov models with distributed state representations. Within this framework, we derive a learning algorithm based on the Expectation--Maximization (EM) procedure for maximum ... -
Fast Learning by Bounding Likelihoods in Sigmoid Type Belief Networks
(1996-02-09)Sigmoid type belief networks, a class of probabilistic neural networks, provide a natural framework for compactly representing probabilistic information in a variety of unsupervised and supervised learning problems. ... -
Information Dissemination and Aggregation in Asset Markets with Simple Intelligent Traders
(1998-09-01)Various studies of asset markets have shown that traders are capable of learning and transmitting information through prices in many situations. In this paper we replace human traders with intelligent software agents ... -
Learning from Incomplete Data
(1995-01-24)Real-world learning tasks often involve high-dimensional data sets with complex patterns of missing features. In this paper we review the problem of learning from incomplete data from two statistical perspectives---the ... -
Learning-Based Approach to Real Time Tracking and Analysis of Faces
(1999-09-23)This paper describes a trainable system capable of tracking faces and facialsfeatures like eyes and nostrils and estimating basic mouth features such as sdegrees of openness and smile in real time. In developing this ... -
Model-Based Matching by Linear Combinations of Prototypes
(1996-12-01)We describe a method for modeling object classes (such as faces) using 2D example images and an algorithm for matching a model to a novel image. The object class models are "learned'' from example images that we call ... -
Model-Based Matching of Line Drawings by Linear Combinations of Prototypes
(1996-01-18)We describe a technique for finding pixelwise correspondences between two images by using models of objects of the same class to guide the search. The object models are 'learned' from example images (also called ... -
Neural Networks
(1996-03-13)We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view ... -
A Note on Object Class Representation and Categorical Perception
(1999-12-17)We present a novel scheme ("Categorical Basis Functions", CBF) for object class representation in the brain and contrast it to the "Chorus of Prototypes" scheme recently proposed by Edelman. The power and flexibility ... -
A Note on Support Vector Machines Degeneracy
(1999-08-11)When training Support Vector Machines (SVMs) over non-separable data sets, one sets the threshold $b$ using any dual cost coefficient that is strictly between the bounds of $0$ and $C$. We show that there exist SVM ... -
A Note on the Generalization Performance of Kernel Classifiers with Margin
(2000-05-01)We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The ... -
Object Detection in Images by Components
(1999-08-11)In this paper we present a component based person detection system that is capable of detecting frontal, rear and near side views of people, and partially occluded persons in cluttered scenes. The framework that is ... -
Pre-Attentive Segmentation in the Primary Visual Cortex
(1998-06-30)Stimuli outside classical receptive fields have been shown to exert significant influence over the activities of neurons in primary visual cortexWe propose that contextual influences are used for pre-attentive visual ... -
Probabilistic Independence Networks for Hidden Markov Probability Models
(1996-03-13)Graphical techniques for modeling the dependencies of randomvariables have been explored in a variety of different areas includingstatistics, statistical physics, artificial intelligence, speech recognition, image ... -
Support Vector Machines: Training and Applications
(1997-03-01)The Support Vector Machine (SVM) is a new and very promising classification technique developed by Vapnik and his group at AT&T Bell Labs. This new learning algorithm can be seen as an alternative training technique ... -
Three-Dimensional Correspondence
(1998-12-01)This paper describes the problem of three-dimensional object correspondence and presents an algorithm for matching two three-dimensional colored surfaces using polygon reduction and the minimization of an energy function. ... -
A Trainable Object Detection System: Car Detection in Static Images
(1999-10-13)This paper describes a general, trainable architecture for object detection that has previously been applied to face and peoplesdetection with a new application to car detection in static images. Our technique is a ...
