paper-with-me

Papers

The Wavefunction of Continuous-Time Recurrent Neural Networks

2021-02-13 · Ikjyot Singh Kohli, Michael C. Haslam

In this paper, we explore the possibility of deriving a quantum wavefunction for continuous-time recurrent neural network (CTRNN). We did this by first starting with a two-dimensional dynamical system that describes the classical dynamics of a continuous-time recurrent neural network, and then deriving a Hamiltonian. After this, we quantized this Hamiltonian on a Hilbert space $\mathbb{H} = L^2(\mathbb{R})$ using Weyl quantization. We then solved the Schrodinger equation which gave us the wavefunction in terms of Kummer's confluent hypergeometric function corresponding to the neural network structure. Upon applying spatial boundary conditions at infinity, we were able to derive conditions/restrictions on the weights and hyperparameters of the neural network, which could potentially give insights on the the nature of finding optimal weights of said neural networks.

📄 PDF Abstract BibTeX arXiv:2102.09399

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory

2026-03-03 · Xuan Zhang, Haiyang Yu, Chengdong Wang, Jacob Helwig 외 arxiv

We aim to learn wavefunctions simulated by time-dependent density functional theory (TDDFT), which can be efficiently represented as linear combination coefficients of atomic orbitals. In real-time TDDFT, the electronic …

First principles physics-informed neural network for quantum wavefunctions and eigenvalue surfaces

2022-11-08 · Marios Mattheakis, Gabriel R. Schleder, Daniel T. Larson, Efthimios Kaxiras

Physics-informed neural networks have been widely applied to learn general parametric solutions of differential equations. Here, we propose a neural network to discover parametric eigenvalue and eigenfunction surfaces of…

Towards a Foundation Model for Neural Network Wavefunctions

2023-03-17 · Michael Scherbela, Leon Gerard, Philipp Grohs

Deep neural networks have become a highly accurate and powerful wavefunction ansatz in combination with variational Monte Carlo methods for solving the electronic Schr\"odinger equation. However, despite their success an…

Variational Monte Carlo

Waveflow: boundary-conditioned normalizing flows applied to fermionic wavefunctions

2022-11-27 · Luca Thiede, Chong Sun, Alán Aspuru-Guzik

An efficient and expressive wavefunction ansatz is key to scalable solutions for complex many-body electronic structures. While Slater determinants are predominantly used for constructing antisymmetric electronic wavefun…

SchrödingeRNN: Generative Modeling of Raw Audio as a Continuously Observed Quantum State

2019-11-26 · Beñat Mencia Uranga, Austen Lamacraft

We introduce Schr\"odingeRNN, a quantum inspired generative model for raw audio. Audio data is wave-like and is sampled from a continuous signal. Although generative modelling of raw audio has made great strides lately, …