Michael Scherbela
@MScherbela
Followers
71
Following
26
Media
1
Statuses
7
PhD student interested in Machine Learning and Physics
Joined May 2021
RT @n_gao96: I am truly excited to share our latest work with @MScherbela, @GrohsPhilipp, and @guennemann on "Accurate Ab-initio Neural-net….
arxiv.org
We present finite-range embeddings (FiRE), a novel wave function ansatz for accurate large-scale ab-initio electronic structure calculations. Compared to contemporary neural-network wave...
0
32
0
RT @GrohsPhilipp: Happy to share that our paper "Towards a transferable fermionic neural wavefunction for molecules", jointly with @MScherb….
0
7
0
RT @JannesNys: Spent the last 2 days at the DL-VMC workshop in Vienna. Very interesting to see the immense progress and ideas on solving el….
0
1
0
RT @GrohsPhilipp: Very happy to share our latest work on solving the electronic Schrödinger equation with deep neur….
arxiv.org
Deep neural networks have become a highly accurate and powerful wavefunction ansatz in combination with variational Monte Carlo methods for solving the electronic Schrödinger equation. However,...
0
6
0
RT @GrohsPhilipp: Happy to announce that our paper "Gold-standard solutions to the Schrödinger equation: how much physics to we need?" join….
arxiv.org
Finding accurate solutions to the Schrödinger equation is the key unsolved challenge of computational chemistry. Given its importance for the development of new chemical compounds, decades of...
0
3
0
RT @NatComputSci: In a recent Article, @Mscherbela, @GrohsPhilipp, @marquetand and colleagues propose weight-sharing neural network-based v….
nature.com
Nature Computational Science - Weight-sharing is used to accelerate and to effectively pretrain neural network-based variational Monte Carlo methods when solving the electronic Schrödinger...
0
15
0