In this article, we present a distributed variant of an adaptive stochastic gradient method for training deep neural networks in the parameter-server model. To reduce communication cost among workers and server, incorporate two types quantization schemes, i.e., weight quantization, into proposed Adam. addition, to bias introduced by operations, propose error-feedback technique compensate quanti...

Recent studies examining the role of self-controlled feedback have shown that learners ask for feedback after what they believe was a "good" rather than "poor" trial. Also, trials on which participants request feedback are often more accurate than those without feedback. The present study examined whether manipulating participants' perception of "good" performance would have differential effect...

Anxiety disorders are the most common reasons for referring to specialized clinics. If the response to stress changed, anxiety can be greatly controlled. The most obvious effect of stress occurs on circulatory system especially through sweating. the electrical conductivity of skin or in other words Galvanic Skin Response (GSR) which is dependent on stress level is used; beside this parameter pe...

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. ...

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...