A comparative analysis of a neural network with calculated weights and a neural network with random generation of weights based on the training dataset size
This addresses efficiency and data scarcity issues in neural network training, but it is incremental as it builds on existing metric recognition methods.
The paper compared a multilayer perceptron with analytically calculated weights versus random initialization on MNIST, finding that the pre-calculated weights enabled much faster training and greater robustness to reduced dataset sizes.
The paper discusses the capabilities of multilayer perceptron neural networks implementing metric recognition methods, for which the values of the weights are calculated analytically by formulas. Comparative experiments in training a neural network with pre-calculated weights and with random initialization of weights on different sizes of the MNIST training dataset are carried out. The results of the experiments show that a multilayer perceptron with pre-calculated weights can be trained much faster and is much more robust to the reduction of the training dataset.