Machine Learning Landscapes
Lead Research Organisation:
University of Cambridge
Department Name: Chemistry
Abstract
This project will involve the characterisation of machine learning landscapes for neural networks. The theory and numerical methods developed for exploring molecular energy landscapes will be applied to the non-convex landscapes defined by the loss function of an artificial neural network. In particular, we will investigate analogues of the density of states to define thermodynamic quantities and rate constants. The resulting insight will be used to define combinations of solutions that provide superior predictive power for applications ranging from molecular geometry optimisation to clinician diagnostic support.
Organisations
People |
ORCID iD |
David John Wales (Primary Supervisor) | |
Conor Cafolla (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/N509620/1 | 30/09/2016 | 29/09/2022 | |||
2275899 | Studentship | EP/N509620/1 | 30/09/2019 | 30/03/2023 | Conor Cafolla |
EP/R513180/1 | 30/09/2018 | 29/09/2023 | |||
2275899 | Studentship | EP/R513180/1 | 30/09/2019 | 30/03/2023 | Conor Cafolla |