Results 1  10
of
622
A framework for studying the neurobiology of valuebased decision making.
 Nat. Rev. Neurosci.
, 2008
"... Valuebased decision making is pervasive in nature. It occurs whenever an animal makes a choice from several alternatives on the basis of a subjective value that it places on them. Examples include basic animal behaviours, such as bee foraging, and complicated human decisions, such as trading in th ..."
Abstract

Cited by 164 (14 self)
 Add to MetaCart
dynamics that are required by different valuedependent learning and decision problems. However, a full understanding of choice will require a description at all these levels. In this Review we propose a framework for thinking about decision making. It has three components: first, it divides decision
SUNDIALS: Suite of Nonlinear and Differential/ Algebraic Equation Solvers
 ACM Trans. Math. Software
, 2005
"... SUNDIALS is a suite of advanced computational codes for solving largescale problems that can be modeled as a system of nonlinear algebraic equations, or as initialvalue problems in ordinary differential or differentialalgebraic equations. The basic versions of these codes are called KINSOL, CVOD ..."
Abstract

Cited by 162 (6 self)
 Add to MetaCart
SUNDIALS is a suite of advanced computational codes for solving largescale problems that can be modeled as a system of nonlinear algebraic equations, or as initialvalue problems in ordinary differential or differentialalgebraic equations. The basic versions of these codes are called KINSOL
Learning with incomplete information in the Committee Machine
, 2009
"... We study the problem of learning with incomplete information in a studentteacher setup for the committee machine. The learning algorithm combines unsupervised Hebbian learning of a series of associations with a delayed reinforcement step, in which the set of previously learnt associations is partly ..."
Abstract
 Add to MetaCart
for overlaps of student and teacher weight vectors, whose solutions provide a complete description of the learning behavior. It reveals complicated dynamics showing that perfect generalization can be obtained if the learning parameter exceeds a threshold λc, and if the initial value of the overlap between
Efficient Memorybased Learning for Robot Control
, 1990
"... This dissertation is about the application of machine learning to robot control. A system which has no initial model of the robot/world dynamics should be able to construct such a model using data received through its sensorsan approach which is formalized here as the $AB (StateActionBehaviour) ..."
Abstract

Cited by 120 (3 self)
 Add to MetaCart
This dissertation is about the application of machine learning to robot control. A system which has no initial model of the robot/world dynamics should be able to construct such a model using data received through its sensorsan approach which is formalized here as the $AB (State
ORIGINAL PAPER Learning with incomplete information in the committee machine
"... Abstract We study the problem of learning with incomplete information in a student–teacher setup for the committee machine. The learning algorithm combines unsupervised Hebbian learning of a series of associations with a delayed reinforcement step, in which the set of previously learnt associations ..."
Abstract
 Add to MetaCart
for overlaps of student and teacher weight vectors, whose solutions provide a complete description of the learning behavior. It reveals complicated dynamics showing that perfect generalization can be obtained if the learning parameter exceeds a threshold λc, and if the initial value of the overlap between
Machine Learning for Helicopter Dynamics Models Machine Learning for Helicopter Dynamics Models
"... Abstract Machine Learning for Helicopter Dynamics Models by Ali Punjani Master of Science in Computer Science University of California, Berkeley Professor Pieter Abbeel, Chair We consider the problem of system identification of helicopter dynamics. Helicopters are complex systems, coupling rigid bo ..."
Abstract
 Add to MetaCart
Abstract Machine Learning for Helicopter Dynamics Models by Ali Punjani Master of Science in Computer Science University of California, Berkeley Professor Pieter Abbeel, Chair We consider the problem of system identification of helicopter dynamics. Helicopters are complex systems, coupling rigid
Machine learning for helicopter dynamics models
, 2014
"... Abstract Machine Learning for Helicopter Dynamics Models by Ali Punjani Master of Science in Computer Science University of California, Berkeley Professor Pieter Abbeel, Chair We consider the problem of system identification of helicopter dynamics. Helicopters are complex systems, coupling rigid bo ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Abstract Machine Learning for Helicopter Dynamics Models by Ali Punjani Master of Science in Computer Science University of California, Berkeley Professor Pieter Abbeel, Chair We consider the problem of system identification of helicopter dynamics. Helicopters are complex systems, coupling rigid
Unorganised Machines in Learning Classifier Systems
, 2008
"... Many representations have been presented to enable the effective evolution of computer programs. Turing was perhaps the first to present a general scheme by which to achieve this end. Significantly, Turing proposed a form of discrete dynamical system and yet dynamical representations remain almost ..."
Abstract
 Add to MetaCart
almost unexplored within genetic programming. This paper presents results from an initial investigation into using Turing’s representation ideas within a Learning Classifier System. It is shown possible to evolve ensembles of dynamical Boolean function networks to solve versions of the well
Discrete Simulation of Dynamical Boundary Value Problems
, 1995
"... INTRODUCTION Problems which depend on continuous variables like time and space are generally modelled by differential equations. If the quantities in this model are considered as input and output signals, then such an idealized description is also called a continuous system. Purely time dependent p ..."
Abstract

Cited by 9 (9 self)
 Add to MetaCart
problems are described by ordinary differential equations (ODE), leading to a onedimensional (or lumped parameter) system. Time and space dependent problems like wave propagation or heat and mass transfer are represented by partial differential equations (PDE), leading to multidimensional (or distributed
Machine Learning in an Auction Environment
"... We consider a model of repeated online auctions in which an ad with an uncertain clickthrough rate faces a random distribution of competing bids in each auction and there is discounting of payoffs. We formulate the optimal solution to this explore/exploit problem as a dynamic programming problem an ..."
Abstract
 Add to MetaCart
to illustrate that the value of incorporating active exploration into a machine learning system in an auction environment is exceedingly small.
Results 1  10
of
622