87 citations · 222 across the 14 of their papers we have counts for
15 papers
Growing Neural Networks: Dynamic Evolution through Gradient Descent
Anil Radhakrishnan, John F. Lindner, Scott T. Miller +2
In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The f…
Solving two-dimensional quantum eigenvalue problems using physics-informed machine learning
Elliott G. Holliday, John F. Lindner, William L. Ditto
A particle confined to an impassable box is a paradigmatic and exactly solvable one-dimensional quantum system modeled by an infinite square well potential. Here we explore some of…
Neuronal diversity can improve machine learning for physics and beyond
Anshul Choudhary, Anil Radhakrishnan, John F. Lindner +2
Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the layers of artificial neural networks. Here we construct neural networks from neurons that lea…
Forecasting Hamiltonian dynamics without canonical coordinates
Anshul Choudhary, John F. Lindner, Elliott G. Holliday +3
Conventional neural networks are universal function approximators, but because they are unaware of underlying symmetries or physical laws, they may need impractically many training…
Mastering high-dimensional dynamics with Hamiltonian neural networks
Scott T. Miller, John F. Lindner, Anshul Choudhary +2
We detail how incorporating physics into neural network design can significantly improve the learning and forecasting of dynamical systems, even nonlinear systems of many dimension…
Chaotic Attractor Hopping yields Logic Operations
K. Murali, Sudeshna Sinha, Vivek Kohar +2
Certain nonlinear systems can switch between dynamical attractors occupying different regions of phase space, under variation of parameters or initial states. In this work we explo…