Gori Marco. (1997). Optimal Learning in Artificial Neural Networks: A Theoretical View. Proc. of Summer School on Rec.NN, Italy. (in press) Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Connectionist Learning of Natural Language Lexical Phonotactics - Stoianov, Nerbonne (1998) (1 citation) (Correct)
....subsection, the interpretation of neuron activation as a probability is used as a key to find the best evaluation method. Finally, details about the last SRN model performance are given in Subsection 4.3. 4.1 Evolutionary approach at training Pool of NN s. As many authors point out [Bengio93] Gori97] Haykin94] the stochastic nature of the training process and the complexity of the task doesn t always direct the network toward the absolute minimum, but quite often to local minima. Sometimes, in spite of applying a momentum term, training with coefficient scheduling (see Haykin94 for ....
Gori Marco. (1997). Optimal Learning in Artificial Neural Networks: A Theoretical View. Proc. of Summer School on Rec.NN, Italy. (in press)
Unimodal Loading Problems - Bianchini, Fanelli, Gori, Protasi Self-citation (Bianchini Gori) (Correct)
....of local minima derives essentially from two different reasons. First, they may arise because of an unsuitable joint choice of the functions which defines the network dynamics and the error function. Second, local minima may be inherently related to the structure of the problem at hand. In [5], these two cases have been referred to as spurious and structural local minima, respectively. Problems of sub optimal solutions may also arise when learning with high initial weights, as a sort of premature neuron saturation arises, which is strictly related to the neuron fan in. An interesting ....
M. Bianchini and M. Gori, Optimal learning in artificial neural networks: a theoretical view. Accepted for publication on Neurocomputing.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC