Show simple item record

Learning with the Adaptive Time-Delay Neural Network

dc.contributor.authorLin, Daw-Tungen_US
dc.contributor.authorLigomenides, Panos A.en_US
dc.contributor.authorDayhoff, Judith E.en_US
dc.description.abstractThe Adaptive Time-delay Neural Network (AT N N), a paradigm for training a nonlinear neural network with adaptive time-delays, is described. Both time delays and connection weights are adapted on-line according to a gradient descent approach, with time delays unconstrained with respect to one another, and an arbitrary number of interconnections with different time delays placed between any two processing units. Weight and time-delay adaptations evolve based on inputs and target outputs consisting of spatiotemporal patterns (e.g. multichannel temporal sequences). The AT N N is used to generate circular and figure- eight trajectories, to model harmonic waves, and to do chaotic time series predictions. Its performance outstrips that of the time-delay neural network (T D N N), which has adaptable weights but fixed time delays. Applications to identification and control as well as signal processing and speech recognition are domains to which this type of network can be appropriately applied.en_US
dc.format.extent1007630 bytes
dc.relation.ispartofseriesISR; TR 1993-49en_US
dc.subjectneural networksen_US
dc.subjectpredictive controlen_US
dc.subjectneural systemsen_US
dc.subjectsignal processingen_US
dc.subjectspeech processingen_US
dc.subjectIntelligent Servomechanismsen_US
dc.titleLearning with the Adaptive Time-Delay Neural Networken_US
dc.typeTechnical Reporten_US

Files in this item


This item appears in the following Collection(s)

Show simple item record