Results 1  10
of
257
A tutorial on support vector machines for pattern recognition
 Data Mining and Knowledge Discovery
, 1998
"... The tutorial starts with an overview of the concepts of VC dimension and structural risk minimization. We then describe linear Support Vector Machines (SVMs) for separable and nonseparable data, working through a nontrivial example in detail. We describe a mechanical analogy, and discuss when SV ..."
Abstract

Cited by 3319 (12 self)
 Add to MetaCart
(Show Context)
The tutorial starts with an overview of the concepts of VC dimension and structural risk minimization. We then describe linear Support Vector Machines (SVMs) for separable and nonseparable data, working through a nontrivial example in detail. We describe a mechanical analogy, and discuss when SVM solutions are unique and when they are global. We describe how support vector training can be practically implemented, and discuss in detail the kernel mapping technique which is used to construct SVM solutions which are nonlinear in the data. We show how Support Vector machines can have very large (even infinite) VC dimension by computing the VC dimension for homogeneous polynomial and Gaussian radial basis function kernels. While very high VC dimension would normally bode ill for generalization performance, and while at present there exists no theory which shows that good generalization performance is guaranteed for SVMs, there are several arguments which support the observed high accuracy of SVMs, which we review. Results of some experiments which were inspired by these arguments are also presented. We give numerous examples and proofs of most of the key theorems. There is new material, and I hope that the reader will find that even old material is cast in a fresh light.
Structured Semidefinite Programs and Semialgebraic Geometry Methods in Robustness and Optimization
, 2000
"... ..."
On the mathematical foundations of learning
 Bulletin of the American Mathematical Society
, 2002
"... The problem of learning is arguably at the very core of the problem of intelligence, both biological and arti cial. T. Poggio and C.R. Shelton ..."
Abstract

Cited by 329 (12 self)
 Add to MetaCart
(Show Context)
The problem of learning is arguably at the very core of the problem of intelligence, both biological and arti cial. T. Poggio and C.R. Shelton
Approximate counting, uniform generation and rapidly mixing markov chains
 Inf. Comput
, 1989
"... The paper studies effective approximate solutions to combinatorial counting and uniform generation problems. Using a technique based on the simulation of ergodic Markov chains, it is shown that, for selfreducible structures, almost uniform generation is possible in polynomial time provided only tha ..."
Abstract

Cited by 318 (11 self)
 Add to MetaCart
The paper studies effective approximate solutions to combinatorial counting and uniform generation problems. Using a technique based on the simulation of ergodic Markov chains, it is shown that, for selfreducible structures, almost uniform generation is possible in polynomial time provided only that randomised approximate counting to within some arbitrary polynomial factor is possible in polynomial time. It follows that, for selfreducible structures, polynomial time randomised algorithms for counting to within factors of the form (1
Stable Function Approximation in Dynamic Programming
 IN MACHINE LEARNING: PROCEEDINGS OF THE TWELFTH INTERNATIONAL CONFERENCE
, 1995
"... The success of reinforcement learning in practical problems depends on the ability tocombine function approximation with temporal difference methods such as value iteration. Experiments in this area have produced mixed results; there have been both notable successes and notable disappointments. Theo ..."
Abstract

Cited by 263 (6 self)
 Add to MetaCart
The success of reinforcement learning in practical problems depends on the ability tocombine function approximation with temporal difference methods such as value iteration. Experiments in this area have produced mixed results; there have been both notable successes and notable disappointments. Theory has been scarce, mostly due to the difficulty of reasoning about function approximators that generalize beyond the observed data. We provide a proof of convergence for a wide class of temporal difference methods involving function approximators such as knearestneighbor, and show experimentally that these methods can be useful. The proof is based on a view of function approximators as expansion or contraction mappings. In addition, we present a novel view of approximate value iteration: an approximate algorithm for one environment turns out to be an exact algorithm for a different environment.
Single Crossing Properties And The Existence Of Pure Strategy Equilibria In Games Of Incomplete Information
 Econometrica
, 1997
"... This paper analyzes a class of games of incomplete information where each agent has ..."
Abstract

Cited by 242 (11 self)
 Add to MetaCart
This paper analyzes a class of games of incomplete information where each agent has
Learning and Design of Principal Curves
, 2000
"... Principal curves have been defined as ``self consistent'' smooth curves which pass through the ``middle'' of a $d$dimensional probability distribution or data cloud. They give a summary of the data and also serve as an efficient feature extraction tool. We take a new approach by ..."
Abstract

Cited by 102 (4 self)
 Add to MetaCart
(Show Context)
Principal curves have been defined as ``self consistent'' smooth curves which pass through the ``middle'' of a $d$dimensional probability distribution or data cloud. They give a summary of the data and also serve as an efficient feature extraction tool. We take a new approach by defining principal curves as continuous curves of a given length which minimize the expected squared distance between the curve and points of the space randomly chosen according to a given distribution. The new definition makes it possible to theoretically analyze principal curve learning from training data and it also leads to a new practical construction. Our theoretical learning scheme chooses a curve from a class of polygonal lines with $k$ segments and with a given total length, to minimize the average squared distance over $n$ training points drawn independently. Convergence properties of this learning scheme are analyzed and a practical version of this theoretical algorithm is implemented. In each iteration of the algorithm a new vertex is added to the polygonal line and the positions of the vertices are updated so that they minimize a penalized squared distance criterion. Simulation results demonstrate that the new algorithm compares favorably with previous methods both in terms of performance and computational complexity, and is more robust to varying data models.
Constructive Algorithms for Structure Learning in Feedforward Neural Networks for Regression Problems
 IEEE Transactions on Neural Networks
, 1997
"... In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add hidden units and weights incrementally until a satisfactory solution is found. By formulating the whole ..."
Abstract

Cited by 87 (2 self)
 Add to MetaCart
(Show Context)
In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add hidden units and weights incrementally until a satisfactory solution is found. By formulating the whole problem as a state space search, we first describe the general issues in constructive algorithms, with special emphasis on the search strategy. A taxonomy, based on the differences in the state transition mapping, the training algorithm and the network architecture, is then presented. Keywords Constructive algorithm, structure learning, state space search, dynamic node creation, projection pursuit regression, cascadecorrelation, resourceallocating network, group method of data handling. I. Introduction A. Problems with Fixed Size Networks I N recent years, many neural network models have been proposed for pattern classification, function approximation and regression problems. Among...
On exact controllability for the NavierStokes equations
 ESAIM: COCV
, 1998
"... Abstract. We study the local exact controllability problem for the NavierStokes equations that describe an incompressible fluid flow in a bounded domain Ω with control distributed in a subdomain! Ω Rn; n 2 f2; 3g. The result that we obtained in this paper is as follows. Suppose that v̂(t; x) is ..."
Abstract

Cited by 67 (1 self)
 Add to MetaCart
(Show Context)
Abstract. We study the local exact controllability problem for the NavierStokes equations that describe an incompressible fluid flow in a bounded domain Ω with control distributed in a subdomain! Ω Rn; n 2 f2; 3g. The result that we obtained in this paper is as follows. Suppose that v̂(t; x) is a given solution of the NavierStokes equations. Let v0(x) be a given initial condition and kv̂(0; )−v0k < " where " is small enough. Then there exists a locally distributed control u; suppu (0; T) ! such that the solution v(t; x) of the NavierStokes equations: