On the Problem of Local Minima in Backpropagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Training a single sigmoidal neuron is hard
Neural Computation
On the efficient classification of data structures by neural networks
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Editorial: Special issue on integration of symbolic and connectionist systems
Cognitive Systems Research
Optimal convergence of on-line backpropagation
IEEE Transactions on Neural Networks
Supervised neural networks for the classification of structures
IEEE Transactions on Neural Networks
A general framework for adaptive processing of data structures
IEEE Transactions on Neural Networks
Performance surfaces of a single-layer perceptron
IEEE Transactions on Neural Networks
On the problem of local minima in recurrent neural networks
IEEE Transactions on Neural Networks
Learning without local minima in radial basis function networks
IEEE Transactions on Neural Networks
On the local minima free condition of backpropagation learning
IEEE Transactions on Neural Networks
Spurious valleys in the error surface of recurrent networks: analysis and avoidance
IEEE Transactions on Neural Networks
An overview of AI research in Italy
Artificial intelligence
Hi-index | 0.00 |
The present work deals with one of the major and not yet completely understood topics of supervised connectionist models. Namely, it investigates the relationships between the difficulty of a given learning task and the chosen neural network architecture. These relationships have been investigated and nicely established for some interesting problems in the case of neural networks used for processing vectors and sequences, but only a few studies have dealt with loading problems involving graphical inputs. In this paper, we present sufficient conditions which guarantee the absence of local minima of the error function in the case of learning directed acyclic graphs with recursive neural networks. We introduce topological indices which can be directly calculated from the given training set and that allows us to design the neural architecture with local minima free error function. In particular, we conceive a reduction algorithm that involves both the information attached to the nodes and the topology, which enlarges significantly the class of the problems with unimodal error function previously proposed in the literature.