The paper offers a critical analysis of the procedure observed in many applications of neural networks. Given a problem to be solved, a favorite NN-architecture is chosen and its p...
Minimization methods for training feed-forward networks with Backpropagation are compared. Feedforward network training is a special case of functional minimization, where no expli...
Syed Muhammad Aqil Burney, Tahseen Ahmed Jilani, C...
In this paper, we consider each neural network as a point in a multi-dimensional problem space and suggest a crossover that locates the central point of a number of neural networks...
— We investigate the use of Particle Swarm Optimization (PSO), and compare with Genetic Algorithms (GA), for a particular robot behavior-learning task: the training of an animat ...
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...