Publications related to Learning of Continuous and Piecewise-Linear Functions With Hessian Total-Variation Regularization

Simulating Learning Dynamics in Project Networks

In this paper we develop a multiagent simulation model to explore the impact of learning dynamics on the productive implementation of innovations in project networks comprised of designers and contractors. Though researchers generally agree that when firms ...

2009

Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward- based Scenarios

Dario Floreano, Claudio Mattiussi, Peter Dürr, Andrea Soltoggio

memory in biological neural networks. Similarly, artificial neural networks could benefit from modulatory dynamics when facing certain types of learning problem. Here we test this hypothesis by introducing modulatory neurons to enhance or dampen neural pla ...

MIT Press2008

Jet-Scheduling Control for SpiderCrane: Experimental Results

Dominique Bonvin, Christophe Salzmann, Philippe Müllhaupt, Davide Buccieri

SpiderCrane is a three-dimensional crane, whose main particularity lies in the absence of large inertial moving parts. This paper presents experimental results obtained with the novel jet-scheduling control methodology that is based on differential flatnes ...

2008

Interferences in the Transformation of Reference Frames during a Posture Imitation Task

Aude Billard, Eric Sauser

We present a biologically-inspired neural model addressing the problem of transformations across frames of reference in a posture imitation task. Our modeling is based on the hypothesis that imitation is mediated by two concurrent transformations selective ...

2007

Extended Hopfield Network for Sequence Learning: Application to Gesture Recognition

Aude Billard, Micha Hersch, André Maurer

In this paper, we extend the Hopfield Associative Memory for storing multiple sequences of varying duration. We apply the model for learning, recognizing and encoding a set of human gestures. We measure systematically the performance of the model against n ...

2005

Time-lag in Derivative Convergence for Fixed Point Iterations

Daniel Kressner

In an earlier study it was proven and experimentally confirmed on a 2D Euler code that fixed point iterations can be differentiated to yield first and second order derivatives of implicit functions that are defined by state equations. It was also asserted ...

2005

$ l _{ p } $ -Multiresolution Analysis: How to Reduce Ringing and Sparsify the Error

Michaël Unser, Thierry Blu

We propose to design the reduction operator of an image pyramid so as to minimize the approximation error in the

l _{ p }

-sense (not restricted to the usual p=2), where p can take non-integer values. The underlying image model is specified using shift- ...

IEEE2002

Regularization Networks for Inverse Problems: A state-space approach

Giancarlo Ferrari Trecate

The solution of linear inverse problems obtained by means of regularization theory has the structure of a neural network similar to classical RBF networks. However, the basis functions depend in a nontrivial way on the specific linear operator to be invert ...

2000

Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition

Hervé Bourlard, Astrid Hagen

In this paper, we present a new approach to incorporating multiple time scale information as independent streams in multi-stream processing. To illustrate the procedure, we take two different sets of multiple time scale features. In the first system, these ...

IDIAP2000

Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition

Hervé Bourlard, Astrid Hagen

In this paper, we present a new approach to incorporating multiple time scale information as independent streams in multi-stream processing. To illustrate the procedure, we take two different sets of multiple time scale features. In the first system, these ...

2000

Learning of Continuous and Piecewise-Linear Functions With Hessian Total-Variation Regularization

Graph Chatbot

Chat with Graph Search

Simulating Learning Dynamics in Project Networks

Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward- based Scenarios

Jet-Scheduling Control for SpiderCrane: Experimental Results

Interferences in the Transformation of Reference Frames during a Posture Imitation Task

Extended Hopfield Network for Sequence Learning: Application to Gesture Recognition

Time-lag in Derivative Convergence for Fixed Point Iterations

$ l _{ p } $ -Multiresolution Analysis: How to Reduce Ringing and Sparsify the Error

Regularization Networks for Inverse Problems: A state-space approach

Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition

Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition

Simulating Learning Dynamics in Project Networks

Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward- based Scenarios

Jet-Scheduling Control for SpiderCrane: Experimental Results

Time-lag in Derivative Convergence for Fixed Point Iterations

$ l _{ p } $ -Multiresolution Analysis: How to Reduce Ringing and Sparsify the Error

Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition

Interferences in the Transformation of Reference Frames during a Posture Imitation Task

Extended Hopfield Network for Sequence Learning: Application to Gesture Recognition

Regularization Networks for Inverse Problems: A state-space approach

Using Multiple Time Scales in the Framework of Multi-Stream Speech Recognition