Continuous-time temporal back-propagation

Day, S.P.; Camporese, P.S.

doi:10.1109/ijcnn.1991.155319

Cited by 5 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly to time-delay neural networks (Day & Davenport, 1993;Lin et al, 1993) each connection in the DRAMA network has two parameters associated with it instead of one: a time parameter (tp) and a confidence factor (cf) (see Figure 4 left). Time parameters and confidence factors are positive numbers (real numbers in the simulation and integers in the physical implementations).…”

Section: Associative Module (Drama)mentioning

confidence: 99%

DRAMA, a Connectionist Architecture for Control and Learning in Autonomous Robots

Billard¹,

Hayes²

1999

Adaptive Behavior

View full text Add to dashboard Cite

Adaptation to their environment is a fundamental capability for living agents, from which autonomous robots could also benefit. This work proposes a connectionist architecture, DRAMA, for dynamic control and learning of autonomous robots. DRAMA stands for dynamical recurrent associative memory architecture. It is a time-delay recurrent neural network, using Hebbian update rules. It allows learning of spatio-temporal regularities and time series in discrete sequences of inputs, in the face of an important amount of noise. The first part of this paper gives the mathematical description of the architecture and analyses theoretically and through numerical simulations its performance. The second part of this paper reports on the implementation of DRAMA in simulated and physical robotic experiments. Training and rehearsal of the DRAMA architecture is computationally fast and inexpensive, which makes the model particularly suitable for controlling computationally-challenged robots. In the experiments, we use a basic hardware system with very limited computational capability and show that our robot can carry out real time computation and on-line learning of relatively complex cognitive tasks. In these experiments, two autonomous robots wander randomly in a fixed environment, collecting information about its elements. By mutually associating information of their sensors and actuators, they learn about physical regularities underlying their experience of varying stimuli. The agents learn also from their mutual interactions. We use a teacher-learner scenario, based on mutual following of the two agents, to enable transmission of a vocabulary from one robot to the other.

show abstract

Section: Associative Module (Drama)mentioning

confidence: 99%

DRAMA, a Connectionist Architecture for Control and Learning in Autonomous Robots

Billard¹,

Hayes²

1999

Adaptive Behavior

View full text Add to dashboard Cite

show abstract

Trajectory production with the adaptive time-delay neural network

1995

View full text Add to dashboard Cite

Continuous-time temporal back-propagation with adaptable time delays

Day

Davenport

1993

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Backpropagation is extended to continuous-time feedforward networks with internal, adaptable time delays. The new technique is suitable for parallel hardware implementation, with continuous multidimensional training signals. The resulting networks can be used for signal prediction, signal production, and spatiotemporal pattern recognition tasks. Unlike conventional backpropagation networks, they can easily adapt while performing true signal prediction. Simulation results are presented for networks trained to predict future values of the Mackey-Glass chaotic signal, using its present value as an input. For this application, networks with adaptable delays had less than half the prediction error of networks with fixed delays, and about one-quarter the error of conventional networks. After training, the network can be operated in a signal production configuration, where it autonomously generates a close approximation to the Mackey-Glass signal.

show abstract

Continuous-time temporal back-propagation

Cited by 5 publications

References 6 publications

DRAMA, a Connectionist Architecture for Control and Learning in Autonomous Robots

DRAMA, a Connectionist Architecture for Control and Learning in Autonomous Robots

Trajectory production with the adaptive time-delay neural network

Continuous-time temporal back-propagation with adaptable time delays

Contact Info

Product

Resources

About