Year: 2024
Type: preprint
Abstract: This paper demonstrates that grokking behavior in modular arithmetic with a modulus P in a neural network can be controlled by modifying the profile of the activation function as well as the depth and width of the model. Plotting the even PCA projections of the weights of the last NN layer against their odd projections further yields patterns which become significantly more uniform when the nonlinearity is increased by incrementing the number of layers. These patterns can be employed to factor P when P is nonprime. Finally, a metric for the generalization ability of the network is inferred from the entropy of the layer weights while the degree of nonlinearity is related to correlations between the local entropy of the weights of the neurons in the final layer.
Source: arXiv (Cornell University)
Authors: Salah, Ahmed, Yevick, David
Institution: University of Waterloo
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4404389522