135 search results - page 2 / 27 » Solving the Ill-Conditioning in Neural Network Learning |
IJCNN
2006
IEEE
13 years 11 months ago
2006
IEEE
— One of the major drawbacks of the Hopfield network is that when it is applied to certain polytopes of combinatorial problems, such as the traveling salesman problem (TSP), the...
ICANN
2007
Springer
13 years 11 months ago
2007
Springer
Abstract. This paper presents Recurrent Policy Gradients, a modelfree reinforcement learning (RL) method creating limited-memory stochastic policies for partially observable Markov...
CORR
2008
Springer
13 years 5 months ago
2008
Springer
The solving of least square systems is a useful operation in neurocomputational modeling of learning, pattern matching, and pattern recognition. In these last two cases, the soluti...
ICANN
2009
Springer
14 years 4 days ago
2009
Springer
Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generati...
NPL
2006
13 years 5 months ago
2006
The authors previously proposed a self-organizing Hierarchical Cerebellar Model Articulation Controller (HCMAC) neural network containing a hierarchical GCMAC neural network and a ...