Sciweavers

147 search results - page 13 / 30
» On the weight dynamics of recurrent learning
Sort
View
WAIM
2009
Springer
14 years 1 months ago
Kernel-Based Transductive Learning with Nearest Neighbors
In the k-nearest neighbor (KNN) classifier, nearest neighbors involve only labeled data. That makes it inappropriate for the data set that includes very few labeled data. In this ...
Liangcai Shu, Jinhui Wu, Lei Yu, Weiyi Meng
ALGORITHMICA
2010
95views more  ALGORITHMICA 2010»
13 years 8 months ago
Homogeneous String Segmentation using Trees and Weighted Independent Sets
We divide a string into k segments, each with only one sort of symbols, so as to minimize the total number of exceptions. Motivations come from machine learning and data mining. F...
Peter Damaschke
NECO
2010
103views more  NECO 2010»
13 years 3 months ago
Population Models of Temporal Differentiation
Temporal derivatives are computed by a wide variety of neural circuits, but the problem of performing this computation accurately has received little theoretical study. Here we sy...
Bryan P. Tripp, Chris Eliasmith
CEC
2008
IEEE
14 years 3 months ago
Neuro-evolving maintain-station behavior for realistically simulated boats
— We evolve a neural network controller for a boat that learns to maintain a given bearing and range with respect to a moving target in the Lagoon 3D game environment. Simulating...
Nathan A. Penrod, David Carr, Sushil J. Louis, Bob...
IJCNN
2007
IEEE
14 years 2 months ago
A Novel Weighted LBG Algorithm for Neural Spike Compression
Abstract— In this paper, we present a weighted Linde-BuzoGray algorithm (WLBG) as a powerful and efficient technique for compressing neural spike data. We compare this technique...
Sudhir Rao, António R. C. Paiva, Jose C. Pr...