NeuroCOLT

Neural Networks and Computational Learning Theory

 

About NeuroCOLT

Papers Archive

1994 1995
1996 1997
1998 1999
2000 2001

Books

info@neurocolt.org

NeuroCOLT Technical Reports 1996

NC-TR-96-001:
On digital nondeterminism
Felipe Cucker, Martin Matamala

NC-TR-96-002:
Complexity and Real Computation: A Manifesto
Lenore Blum, Felipe Cucker, Mike Shub, Steve Smale

NC-TR-96-003:
Models for Parallel Computation with Real Numbers
F. Cucker, J.L. Montana, L.M. Pardo

NC-TR-96-004:
Nash Trees and Nash Complexity
Felipe Cucker, Thomas Lickteig

NC-TR-96-005:
On the computational power and super-Turing capabilities of dynamical systems
Olivier Bournez, Michel Cosnard

NC-TR-96-006:
Finite Sample Size Results for Robust Model Selection; Application to
Neural Networks

Joel Ratsaby, Ronny Meir

NC-TR-96-007:
On the structure of $\npoly{C}$
Gregorio Malajovich, Klaus Meer

NC-TR-96-008:
Dynamic Recurrent Neural Networks: a Dynamical Analysis
Jean-Philippe DRAYE, Davor PAVISIC, Guy CHERON, Gaëtan LIBERT

NC-TR-96-009:
Scale-sensitive Dimensions, Uniform Convergence, and Learnability
Noga Alon, Shai Ben-David, Nicolò Cesa-Bianchi, David Haussler

NC-TR-96-010:
On-line Prediction and Conversion Strategies
Nicolò Cesa-Bianchi,Yoav Freund, David P. Helmbold, Manfred K. Warmuth

NC-TR-96-011:
Worst-case Quadratic Loss Bounds for Prediction Using Linear Functions and Gradient Descent
Nicolò Cesa-Bianchi, Philip M. Long, Manfred K. Warmuth

NC-TR-96-012:
Using Bayesian Methods for Avoiding Overfitting and for Ranking Networks in Multilayer Perceptrons Learning
Michel de Bollivier, Domenico Perrotta

NC-TR-96-013:
Lower Bounds for the Computational Power of Networks of Spiking Neurons
Wolfgang Maass

NC-TR-96-014:
Analog Computations on Networks of Spiking Neurons
Wolfgang Maass

NC-TR-96-015:
Vapnik-Chervonenkis Dimension of Neural Nets
Wolfgang Maass

NC-TR-96-016:
On the Computational Power of Noisy Spiking Neurons
Wolfgang Maass

NC-TR-96-017:
Die Komplexität des Rechnens und Lernens mit neuronalen Netzen --
Ein Kurzführer

Michael Schmitt

NC-TR-96-018:
Tracking the best disjunction
Peter Auer, Manfred Warmuth

NC-TR-96-019:
Learning Nested Differences in the Presence of Malicious Noise
Peter Auer

NC-TR-96-020:
Characterizing the Learnability of Kolmogorov Easy Circuit Expressions
Jose L. Balcazar, Harry Buhrman

NC-TR-96-021:
T2 - Computing optimal 2-level decision tree
Peter Auer

NC-TR-96-022:
Efficient Learning with Virtual Threshold Gates
Wolfgang Maass, Manfred Warmuth

NC-TR-96-023:
On learnability and predicate logic (Extended Abstract)
Wolfgang Maass  Gy. Turan,

NC-TR-96-024:
Lower Bounds on Identification Criteria for Perceptron-like Learning Rules
Michael Schmitt

NC-TR-96-025:
On Methods to Keep Learning Away from Intractability (Extended abstract)
Michael Schmitt

NC-TR-96-026:
Accuracy of techniques for the logical analysis of data
Martin Anthony

NC-TR-96-027:
Interpolation and Learning in Artificial Neural Networks
Martin Anthony

NC-TR-96-028:
Threshold Functions, Decision Lists, and the Representation of Boolean
Functions

Martin Anthony

NC-TR-96-029:
Learning of Depth Two Neural Nets with Constant Fan-in at the Hidden Nodes
Peter Auer, Stephen Kwek, Wolfgang Maass, Manfred K. Warmuth,

NC-TR-96-030:
Exponentially many local minima for single neurons
Peter Auer, Mark Herbster, Manfred K. Warmuth

NC-TR-96-031:
An Efficient Implementation of Sigmoidal Neural Nets in Temporal
Coding with Noisy Spiking Neurons

Wolfgang Maass

NC-TR-96-032:
A Framework for Stuctural Risk Minimisation
John Shawe-Taylor, Peter Bartlett, Robert Williamson, Martin Anthony

NC-TR-96-033:
Learning to Compress Ergodic Sources
by Jonathan Baxter, John Shawe-Taylor

NC-TR-96-034:
Theory and Applications of Agnostic PAC-Learning with Small Decision Trees
Peter Auer, Robert C. Holte, Wolfgang Maass

NC-TR-96-035:
A recurrent network that performs a context-sensitive prediction task
Mark Steijvers, Peter Grünwald

NC-TR-96-036:
Tight worst-case loss bounds for predicting with expert advice
David Haussler, Jyrki Kivinen, Manfred K. Warmuth

NC-TR-96-037:
Exponentiated Gradient Versus Gradient Descent for Linear Predictors
by Jyrki Kivinen, Manfred K. Warmuth

NC-TR-96-038:
Active Noise Control with Dynamic Recurrent Neural Networks
Davor Pavisic, Laurent Blondel, Jean-Philipe Draye, Gaëtan Libert,  Pierre Chapelle

NC-TR-96-039:
A Survey on real Structural Complexity Theory
Klaus Meer, Christian Michaux

NC-TR-96-040:
The Computational Power of Spiking Neurons Depends on the Shape of the Postsynaptic Potentials
Wolfgang Maass, Berthold Ruf

NC-TR-96-041:
Finding Optimal Multi-Splits for Numerical Attributes in Decision Tree Learning
Tapio Elomaa, Juho Rousu

NC-TR-96-042:
Shattering all Sets of k points in `General Position' Requires (k-1)/2
Parameters

Eduardo D. Sontag

NC-TR-96-043:
Elimination of Constants from Machines over Algebraically Closed Fields
Pascal Koiran

NC-TR-96-044:
Hilbert's Nullstellensatz is in the Polynomial Hierarchy
Pascal Koiran

NC-TR-96-045:
Networks of Spiking Neurons: The Third Generation of Neural Network Models
Wolfgang Maass

NC-TR-96-046:
Use Of Neural Network Ensembles for Portfolio Selection and Risk Management
D.L.Toulson, S.P.Toulson

NC-TR-96-047:
A Graph-theoretic Generalization of the Sauer-Shelah Lemma
Nicolò Cesa-Bianchi, David Haussler

NC-TR-96-048:
A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks
Frederic Gruau, Darrell Whitley

NC-TR-96-049:
Extended Grzegorczyk Hierarchy in the BSS Model of Computability
Jean-Sylvestre Gakwaya

NC-TR-96-050:
Learning from Examples and Side Information
Joel Ratsaby, Vitaly Maiorov

NC-TR-96-051:
Complexity and Dimension
Felipe Cucker, Pascal Koiran, Martin Matamala

NC-TR-96-052:
Semi-Algebraic Complexity -- Additive Complexity of Diagonalization of  QuadraticForms
Thomas Lickteig, Klaus Meer

NC-TR-96-053:
Structural Risk Minimization over Data-Dependent Hierarchies
John Shawe-Taylor, Peter Bartlett, Robert Williamson, Martin Anthony

NC-TR-96-054:
Confidence Estimates of Classification Accuracy on New Examples
John Shawe-Taylor