Supermasks: A Simple Introduction and Implementation in PyTorch

Author(s): Kourosh T. Baghaei

Originally published on Towards AI.

The general understanding of neural networks is that computations are required in order to adjust the weights of a neural network so that it could perform a certain task on a given dataset. However, it seems like it is not quite true. Apparently, given a randomly initialized dense neural network:

There exist sub-networks that when trained, can achieve a performance as well as the original network after training.Even more surprising, there exist sub-networks that without any training, can perform way better than the random initialization on a certain task. For example, on the MNIST dataset, it can achieve up to 86%… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI