7 search results - page 1 / 2 » Adaptation of Artificial Neural Networks Avoiding Catastroph... |
IJCNN
2006
IEEE
13 years 10 months ago
2006
IEEE
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
CONNECTION
2004
13 years 4 months ago
2004
While humans forget gradually, highly distributed connectionist networks forget catastrophically: newly learned information often completely erases previously learned information. ...
NN
1998
Springer
13 years 3 months ago
1998
Springer
Distributed coding at the hidden layer of a multi-layer perceptron (MLP) endows the network with memory compression and noise tolerance capabilities. However, an MLP typically req...
ANNPR
2008
Springer
13 years 6 months ago
2008
Springer
Abstract. Automatic pattern classifiers that allow for on-line incremental learning can adapt internal class models efficiently in response to new information without retraining fr...
ECAL
2007
Springer
13 years 10 months ago
2007
Springer
Abstract. This paper investigates the processes used by an evolved, embodied simulated agent to adapt to large disruptive changes in its sensor morphology, whilst maintaining perfo...