paper-with-me

Papers

Perspective: Energy Landscapes for Machine Learning

2017-03-23 · Andrew J. Ballard, Ritankar Das, Stefano Martiniani, Dhagash Mehta, Levent Sagun, Jacob D. Stevenson, David J. Wales

Machine learning techniques are being increasingly used as flexible non-linear fitting and prediction tools in the physical sciences. Fitting functions that exhibit multiple solutions as local minima can be analysed in terms of the corresponding machine learning landscape. Methods to explore and visualise molecular potential energy landscapes can be applied to these machine learning landscapes to gain new insight into the solution space involved in training and the nature of the corresponding predictions. In particular, we can define quantities analogous to molecular structure, thermodynamics, and kinetics, and relate these emergent properties to the structure of the underlying landscape. This Perspective aims to describe these analogies with examples from recent applications, and suggest avenues for new interdisciplinary research.

📄 PDF Abstract BibTeX arXiv:1703.07915

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Exploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange

2025-01-28 · Haoyang Zheng, Hengrong Du, Ruqi Zhang, Guang Lin

Gradient-based Discrete Samplers (GDSs) are effective for sampling discrete energy landscapes. However, they often stagnate in complex, non-convex settings. To improve exploration, we introduce the Discrete Replica EXcha…

Physics-Inspired Interpretability Of Machine Learning Models

2023-04-05 · Maximilian P Niroomand, David J Wales

The ability to explain decisions made by machine learning models remains one of the most significant hurdles towards widespread adoption of AI in highly sensitive areas such as medicine, cybersecurity or autonomous drivi…

Autonomous DrivingDecision Making

Clustering Molecular Energy Landscapes by Adaptive Network Embedding

2024-01-19 · Paula Mercurio, Di Liu

In order to efficiently explore the chemical space of all possible small molecules, a common approach is to compress the dimension of the system to facilitate downstream machine learning tasks. Towards this end, we prese…

ClusteringNetwork Embedding

First-passage times in complex energy landscapes: a case study with nonmuscle myosin II assembly

2022-04-07 · Rick Bebon, Ulrich S. Schwarz

Complex energy landscapes often arise in biological systems, e.g. for protein folding, biochemical reactions or intracellular transport processes. Their physical effects are often reflected in the first-passage times ari…

Protein Folding

Black holes and the loss landscape in machine learning

2023-06-26 · Pranav Kumar, Taniya Mandal, Swapnamay Mondal

Understanding the loss landscape is an important problem in machine learning. One key feature of the loss function, common to many neural network architectures, is the presence of exponentially many low lying local minim…