Sciweavers

61 search results - page 10 / 13
» neco 2008
Sort
View
NECO
2008
112views more  NECO 2008»
13 years 9 months ago
Second-Order SMO Improves SVM Online and Active Learning
Iterative learning algorithms that approximate the solution of support vector machines (SVMs) have two potential advantages. First, they allow for online and active learning. Seco...
Tobias Glasmachers, Christian Igel
NECO
2008
116views more  NECO 2008»
13 years 9 months ago
A (Somewhat) New Solution to the Variable Binding Problem
To perform automatic, unconscious inference, the human brain must solve the "binding problem" by correctly grouping properties with objects. Temporal binding models like...
Leon Barrett, Jerome Feldman, Liam Mac Dermed
NECO
2008
60views more  NECO 2008»
13 years 9 months ago
Sleeping Our Way to Weight Normalization and Stable Learning
The functions of sleep have been an enduring mystery. Recently, Tononi and Cirelli hypothesized that one of the functions of slow-wave sleep is to scale down synapses in the corte...
Thomas J. Sullivan, Virginia R. de Sa
NECO
2008
156views more  NECO 2008»
13 years 9 months ago
Dynamical Constraints on Using Precise Spike Timing to Compute in Recurrent Cortical Networks
ns. We have previously developed an abstract dynamical system for networks of spiking neurons that has allowed us to identify the criterion for the stationary dynamics of a network...
Arunava Banerjee, Peggy Seriès, Alexandre P...
NECO
2008
101views more  NECO 2008»
13 years 9 months ago
On the Classification Capability of Sign-Constrained Perceptrons
The perceptron (also referred to as McCulloch-Pitts neuron, or linear threshold gate) is commonly used as a simplified model for the discrimination and learning capability of a bi...
Robert A. Legenstein, Wolfgang Maass