Neural Networks: Single-Layer Control

In course

Description

This lecture covers the implementation of a single-layer neural network controller using Webots simulation software. It explains the differences between artificial neurons, perceptrons, and single-layer neural networks. The lecture also discusses transfer functions, the addition of a third sensor, and the impact of sensor numbers on behavior complexity. Furthermore, it explores the efficiency of neuron usage, dataset generation, and varying network architectures in solving tasks. The session concludes with an overview of Boids rules for collective behavior.

Instructor

Official source

https://mediaspace.epfl.ch/media/0_nkjfub04

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (33)

Related concepts (32)

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.

Perceptrons (book)

Perceptrons: an introduction to computational geometry is a book written by Marvin Minsky and Seymour Papert and published in 1969. An edition with handwritten corrections and additions was released in the early 1970s. An expanded edition was further published in 1987, containing a chapter dedicated to counter the criticisms made of it in the 1980s. The main subject of the book is the perceptron, a type of artificial neural network developed in the late 1950s and early 1960s.

Collective animal behavior

Collective animal behaviour is a form of social behavior involving the coordinated behavior of large groups of similar animals as well as emergent properties of these groups. This can include the costs and benefits of group membership, the transfer of information, decision-making process, locomotion and synchronization of the group. Studying the principles of collective animal behavior has relevance to human engineering problems through the philosophy of biomimetics.

Multilayer perceptron

A multilayer perceptron (MLP) is a misnomer for a modern feedforward artificial neural network, consisting of fully connected neurons with a nonlinear kind of activation function, organized in at least three layers, notable for being able to distinguish data that is not linearly separable. It is a misnomer because the original perceptron used a Heaviside step function, instead of a nonlinear kind of activation function (used by modern networks).

Perceptron

In machine learning, the perceptron (or McCulloch-Pitts neuron) is an algorithm for supervised learning of binary classifiers. A binary classifier is a function which can decide whether or not an input, represented by a vector of numbers, belongs to some specific class. It is a type of linear classifier, i.e. a classification algorithm that makes its predictions based on a linear predictor function combining a set of weights with the feature vector.