Realtime Visualization of the Learning Processes in the LAPART Neural Architecture as it Controls a Simulated Autonomous Vehicle

Authors:
Affiliations:
Venue:
IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3 - Volume 3
Year:
2000

Citing 0
Cited 2

eLoom and Flatland: specification, simulation and visualization engines for the study of arbitrary hierarchical neural architectures

Neural Networks - 2003 Special issue: Advances in neural networks research — IJCNN'03
Framework for the interactive learning of artificial neural networks

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Using a neural network as an abstract black box makes it hard to grasp its inner workings and so we may easily miss significant information about the network learning process. Interdependencies between the network and its associated complex model simulation may be even harder to interpret. Visualizing a dynamic functioning neural network along with its related model simulation may lead to a deeper comprehension of both. We propose using a virtual environment as a tool to investigate the complex space of a neural network. As an example, we train a simulated remote autonomous vehicle to locomote a preplanned path through a set of obstacles using a LAPART neural network. Within the virtual environment, we can easily and naturally position ourselves to best observe the activity in which we are most interested and discover the evolving space of an operating neural network.