Results 1  10
of
21
Learning to Achieve Goals
 IN PROC. OF IJCAI93
, 1993
"... Temporal difference methods solve the temporal credit assignment problem for reinforcement learning. An important subproblem of general reinforcement learning is learning to achieve dynamic goals. Although existing temporal difference methods, such as Q learning, can be applied to this problem, they ..."
Abstract

Cited by 31 (1 self)
 Add to MetaCart
, they do not take advantage of its special structure. This paper presents the DGlearning algorithm, which learns efficiently to achieve dynamically changing goals and exhibits good knowledge transfer between goals. In addition, this paper shows how traditional relaxation techniques can be applied
An Efficient and Simplest Algorithm for Generating Diagrams
"... Abstract—Whenever a system is to be designed and modeled, diagrams play a key role in the context. As diagrams enable us to understand, visualize and communicate concepts without ambiguity. Thus for the purpose many diagramming softwares are available. Different softwares uses different methodology ..."
Abstract
 Add to MetaCart
for design and development but with the time the design is becoming complicated day by day and with the increased complexity also increases the learning time for the users. In contrast, software based on easy algorithm is easily understandable by the user. This paper presents a simple and efficient algorithm
Active Learning Algorithms for Neural Networks
"... ......_.ad Five neural algorithms are described that have been derived from an incremental Je..iDg framew.prk, called GENIAL. The GENIAL learning employs four learning elements Ia adapt the network structure and weights while exploring its environment to acquire...el. informatiotl. The common featu ..."
Abstract
 Add to MetaCart
......_.ad Five neural algorithms are described that have been derived from an incremental Je..iDg framew.prk, called GENIAL. The GENIAL learning employs four learning elements Ia adapt the network structure and weights while exploring its environment to acquire...el. informatiotl. The common
Designing the intelligent controller for photovoltaic system in islanding mode operation
"... In this paper, an optimal controller is proposed to control the voltage of photovoltaic system as distributed generation (DG) using intelligent algorithm in islanding mode operation. The control algorithm used in the studied control plant during load variations is based on the reinforcement learnin ..."
Abstract
 Add to MetaCart
In this paper, an optimal controller is proposed to control the voltage of photovoltaic system as distributed generation (DG) using intelligent algorithm in islanding mode operation. The control algorithm used in the studied control plant during load variations is based on the reinforcement
!()+, ./01 23456
, 1995
"... Computing the maximum bichromatic discrepancy is an interesting theoretical problem with important applications in computational learning theory, computational geometry and computer graphics. In this paper we give algorithms to compute the maximum bichromatic discrepancy for simple geometric ranges, ..."
Abstract
 Add to MetaCart
Computing the maximum bichromatic discrepancy is an interesting theoretical problem with important applications in computational learning theory, computational geometry and computer graphics. In this paper we give algorithms to compute the maximum bichromatic discrepancy for simple geometric ranges
DSGA1003/CSCIGA.2567 Problem Set 3 1 Machine Learning and Computational Statistics, Fall 2014
"... problem set policy on the course web site. Instructions. You may use the programming language of your choice. However, you are not permitted to use or reference any machine learning code or packages not written by yourself, except for question 2(d)(g). Your answers to the below questions, including ..."
Abstract
 Add to MetaCart
problem set policy on the course web site. Instructions. You may use the programming language of your choice. However, you are not permitted to use or reference any machine learning code or packages not written by yourself, except for question 2(d)(g). Your answers to the below questions
Monotone Boolean Functions with s Zeros Farthest from Threshold Functions
"... Let Tt denote the tthreshold function on the ncube: Tt(x) = 1 if {i: xi = 1}  ≥ t, and 0 otherwise. Define the distance between Boolean functions g and h, d(g, h), to be the number of points on which g and h disagree. We consider the following extremal problem: Over a monotone Boolean function ..."
Abstract
 Add to MetaCart
for the case t = ⌈n/2 ⌉ and s = 2 n−1 by Blum, Burch, and Langford [BBL98FOCS98], who considered the problem to analyze the behavior of a learning algorithm for monotone Boolean functions, and the previous work for the same t and s by Amano and Maruoka [AM02ALT02]. 1
Finding Small Dominating Sets in Stationless Mobile Packet Radio Networks
, 1991
"... We model a snapshot of a mobile packet radio network as an undirected graph. The nodes of the graph are processors, that communicate along their incident edges by broadcast. The radios do not know the size of the network, and start out with no topological information. Our goal is to select a small s ..."
Abstract
 Add to MetaCart
that for graphs of regular degree, 6, our algorithm has communication complexity of O(IDgl63 + N6), where Dg is the dominating set picked by the algorithm. The time complexity is O(IDgl). Thus the algorithm is efficient for graphs with diameter greater than 3.
A Computational Principle for Hippocampal Learning and
"... ABSTRACT: In the three decades since Marr put forward his computational theory of hippocampal coding, many computational models have been built on the same key principles proposed by Marr: sparse representations, rapid Hebbian storage, associative recall and consolidation. Most of these models have ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
focused on either the CA3 or CA1 fields, using ‘‘offtheshelf’’ learning algorithms such as competitive learning or Hebbian pattern association. Here, we propose a novel coding principle that is common to all hippocampal regions, and from this one principal, we derive learning rules for each of the major
A SpaceTime Discontinuous Galerkin Method for NavierStokes with Recovery
, 2011
"... I appreciate my loving mother, Katherine, for teaching me to rely on myself and to stand tall. I thank my dad, Alan, for allowing me to pursue my love for science. Thank you my brother, Michael, for taking care of me when I was almost dead on the hospital bed. I am thankful for my wonderful pets, Mi ..."
Abstract
 Add to MetaCart
, Miumiu and Momo, for accompanying me through day and night, and through ups and downs. I am grateful for Hung Huynh's enthusiasm and advice in CFD. Cheers to my research comrade, Loc, for enduring my eccentricity. Lastly, I am infinitely happy for this wonderful lifelearning experience with my
Results 1  10
of
21