Publication

Attractor learning with nonlinear, artificial, neural network

2003
Conference Papers

Abstract

A nonlinear recurrent neural network is trained to synthesize chaotic signals. The identification process is reduced to a teaching phase and a linear regression. The influence of the shape of the nonlinearity in the neurons and the noise amplitude are studied, as a result some design rules can be given. In a future step we want this system to be brought to synchronize in a way to perform signal classification.

Official source

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

2003
Conference Papers

Abstract

Official source

Related concepts (32)

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

Related publications (32)

Attractor learning with nonlinear, artificial, neural network

Chat with Graph Search

Load history effects in fiber–polymer composites: A CRNN-based hybrid deep learning approach for fatigue life prediction and structural health monitoring via infrared thermography

Learning and Control with Generalization and Stability Certificates

Sequence Modeling Architectures: Foundations [Special Issue on the Mathematics of Deep Learning]