Stochastic optimization algorithms typically use learning rate schedules that behave asymptotically as J.t(t) = J.to/t. The ensemble dynamics (Leen and Moody, 1993) for such algorithms provides an easy path to results on mean squared weight error and asymptotic normality. We apply this approach to stochastic gradient algorithms with momentum. We show that at late times, learning is governed by ...

Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case performance, leading to suboptimal performance on easy instances, for example when there exists an action that is significantly better than all others. We propose a new...

! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! Though personalized learning has been a goal of educators since the days of Aristotle and private tutors, it is only relatively recently that technological and socio-cultural drivers have made personalized learning at scale possible. The development of digital technologies that allow for the analysis of large volumes of student data, combined with greater a...

Combinatorial auction, where bidders can bid on bundles of items, has been the subject of increasing interest in recent years. Although much research work has been conducted on combinatorial auctions, most has been focusing on the winner determination problem. A largely unexplored area of research in combinatorial auctions is the design of bidding strategies, in particular, those that can be us...

In this paper, several neural network and statistical learning approaches are proposed that learn to make human like decisions for the job assignment problem of the US Navy. Comparison study of Feedforward Neural Networks (FFNN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM) and Adaptive Bayes (AB) classifier with Generalized Estimation Equation (GEE) is provided. ...

Prior experiences can influence future actions. These experiences can not only drive adaptive changes in motor output, but they can also modulate the rate at which these adaptive changes occur. Here we studied anterograde interference in motor adaptation--the ability of a previously learned motor task (Task A) to reduce the rate of subsequently learning a different (and usually opposite) motor ...

keywords: adaptive control, biped walking, learning control, neural networks An adaptive static balance scheme was implemented on an experimental biped. The control scheme used pre-planned but adaptive motion sequences in combination with closed loop reactive control. CMAC neural networks were responsible for the adaptive control of side-to-side and front-to-back balance. Qualitative and quanti...

Abstract Personalized and adaptive learning has been touted to be one of the most promising emerging tools for increasing student success. Yet, terms are neither precise nor clearly defined at this time, thus making it difficult institutions higher education adopt implement a approach using technology that is in its infancy not understood by those who will utilizing it. One goal chapter define ...

Evolving of information and communication based distance education system is began with learning management system (LMS). This type of distance education can be called as asynchronous model. Then, web conferencing software is added to the LMS, so synchronous model is obtained. After that, distance education is evolving from static to adaptive system. This adaptive system should be taken into ac...

This paper describes and evaluates how confidence values can be used to improve the quality of exploration in QRouting for adaptive packet routing in communication networks. In Q-Routing each node in the network has a routing decision maker that adapts, on-line, to learn routing policies that can sustain high network loads and have low average packet delivery time. These decision makers maintai...