Neural Architecture and Hyper-parameter Search for Deep Learning

PI Name Prasanna Balaprakash, MCS
PI Institution Argonne National Laboratory
Project Description

The project Prasanna will be working on is ‘Neural Architecture Search’. Currently, deep learning has gained significant attention in the field of computer science, achieving state-of-the-art results in the fields such as computer vision, speech recognition and text processing. However, the application of deep learning in scientific fields has been mainly discouraged due to lack of domain expertise in designing the deep neural architectures for scientific problems. In this project, our goal is to automate the deep neural architecture search for building deep learning models for scientific datasets. Therefore, we would need access to GPUs for training and evaluating our deep neural network architectures for the ‘Neural Architecture Search’ project.

Testbed

Maud and Neddy