About this document
Enhancing CNNs with Scattering Transform by api-286637373 is a document available to read on EtoBox.
This project aims to improve the data efficiency of convolutional neural networks (CNNs) for image classification tasks. Specifically, the project will use the scattering transform, which extracts similar image features as CNN filters, to help CNNs train faster and with less data. The goal is for the scattering transform to emulate a CNN without needing as much training data or computational power. This improved method could enable automatic image analysis in materials science and neuroscience where collect
- Author
- api-286637373
- Language
- EN