117 citations · 534 across the 30 of their papers we have counts for
5 papers · 1 filter
One-Shot Transfer Learning of Physics-Informed Neural Networks
Shaan Desai, Marios Mattheakis, Hayden Joy +2
Solving differential equations efficiently and accurately sits at the heart of progress in many areas of scientific research, from classical dynamical systems to quantum mechanics.…
Unsupervised Reservoir Computing for Solving Ordinary Differential Equations
Marios Mattheakis, Hayden Joy, Pavlos Protopapas
There is a wave of interest in using unsupervised neural networks for solving differential equations. The existing methods are based on feed-forward networks, {while} recurrent neu…
Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems
Shaan Desai, Marios Mattheakis, David Sondak +2
Accurately learning the temporal behavior of dynamical systems requires models with well-chosen learning biases. Recent innovations embed the Hamiltonian and Lagrangian formalisms…
Encoding Involutory Invariances in Neural Networks
Anwesh Bhattacharya, Marios Mattheakis, Pavlos Protopapas
In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the…
A New Artificial Neuron Proposal with Trainable Simultaneous Local and Global Activation Function
Tiago A. E. Ferreira, Marios Mattheakis, Pavlos Protopapas
The activation function plays a fundamental role in the artificial neural network learning process. However, there is no obvious choice or procedure to determine the best activatio…