Explore groundbreaking research in computational physics through this HEDS seminar presented by Matthew Foulkes on February 4th, 2021. Delve into innovative approaches for solving the complex many-electron Schrödinger equation using deep neural networks. Gain insights into cutting-edge techniques that merge quantum mechanics with machine learning, potentially revolutionizing our understanding of electronic structures in materials science and chemistry. Learn how these advanced computational methods can enhance the accuracy and efficiency of simulating quantum systems, opening new possibilities for predicting material properties and designing novel compounds.
Solving the Many-Electron Schrödinger Equation with Deep Neural Networks
Inside Livermore Lab via YouTube
Overview
Syllabus
HEDS | Solving the Many-Electron Schrödinger Equation with Deep Neural Network
Taught by
Inside Livermore Lab
Related Courses
-
Ab-initio Variational Wave Functions for the Time-(In)dependent Many-electron Schrödinger Equation
-
Approximating Many-Electron Wave Functions Using Neural Networks - IPAM at UCLA
-
Quantum Many-Body Simulations Using Artificial Neural Networks
-
Solving the Time-Dependent Schrödinger Equation with Finite Difference Method in Python
-
Simulation of Quantum Many-Body Systems with Neural Quantum States - Part 2
-
Neural-Network Wave Functions for Quantum Chemistry - IPAM at UCLA
