Backpropagation and contrastive Hebbian learning are two methods of training networks with hidden neurons. Backpropagation computes an error signal for the output neurons and spreads it over the hidden neurons. Contrastive Hebbian learning involves clamping the output neurons at desired values and letting the effect spread through feedback connections over the entire network. To investigate the...

Computational theory of motor control suggests that the brain continuously monitors motor commands, to predict their sensory consequences before actual sensory feedback becomes available. Such prediction error is a driving force of motor learning, and therefore appropriate associations between motor commands and delayed sensory feedback signals are crucial. Indeed, artificially introduced delay...

Rumelhart & Zipser's (1986) competitive learning algorithm is an account of unsupcrvised learning and, as such, might be considered a potential model of free classification behavior in humans. However, selective learning effects (e.g. Dickinson, Shanks & Evenden, 1984) suggest that human learning, ai least under conditions of feedback, may be better characterized by an error-correcting system. ...

This thesis develops a framework for low-complexity communication over channels with feedback. In this framework, which is referred to in the thesis as the compressed-error-cancellation framework, data are sent via a sequence of messages: the first message contains the original data; each subsequent message contains a source-coded description of the channel distortions introduced on the message...

Adaptive behavior requires an organism to evaluate the outcome of its actions, such that future behavior can be adjusted accordingly and the appropriate response selected. During associative learning, the time at which such evaluative information is available changes as learning progresses, from the delivery of performance feedback early in learning to the execution of the response itself durin...

The present study-both qualitative and quantitative--explored fifty EFL learners’ preferences for receiving error feedback on different grammatical units as well as their beliefs about teacher feedback strategies. The study also examined the effect of the students’ level of writing ability on their views about the importance of teacher feedback on different error types. Data was gathered throug...

We propose a new parallel-hierarchical neural network model to enable motor learning for simultaneous control of both trajectory and force. by integrating Hogan's control method and our previous neural network control model using a feedback-error-learning scheme. Furthermore. two hierarchical control laws which apply to the model, are derived by using the Moore-Penrose pseudoinverse matrix. One...

The oculomotor neural integrator is a brainstem nucleus that stores the short term memory of eye position during gaze holding. This neural integrator is believed to perform temporal integration of transient eye velocity input using positive feedback. Such models of integration are known to suffer from a fine-tuning problem [9] since changes in the amount of feedback by less than 10% can de-tune...

This paper investigates a learning control using iterative error compensation for uncertain systems to enhance the precision of high speed, computer controlled machining process. It is especially useful in mass-produced parts produced by high speed machines tool system. This method uses iterative learning technique which adopts machine commands and cutting error experienced in previous maneuver...