We present a method for controlling a dynamical system using real-time fMRI. The objective for the subject in the MR scanner is to balance an inverted pendulum by activating the le...
Anders Eklund, Henrik Ohlsson, Mats T. Andersson...
We propose a competitive finite mixture of neurons (or perceptrons) for solving binary classification problems. Our classifier includes a prior for the weights between different n...
Karthik Sridharan, Matthew J. Beal, Venu Govindara...
This paper proposes an efficient three-stage classifier for handwritten digit recognition based on NN (Neural Network) and SVM (Support Vector Machine) classifiers. The classifica...
Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more ...
In this paper we introduce Ant-Q, a family of algorithms which present many similarities with Q-learning (Watkins, 1989), and which we apply to the solution of symmetric and asymm...