48 citations · 94 across the 8 of their papers we have counts for
8 papers
Divine Benevolence is an : GLUs scale asymptotically faster than MLPs
Alejandro Francisco Queiruga
Scaling laws can be understood from ground-up numerical analysis, where traditional function approximation theory can explain shifts in model architecture choices. GLU variants now…
Interpretability and Generalization Bounds for Learning Spatial Physics
Alejandro Francisco Queiruga, Theo Gutman-Solo, Shuai Jiang
While there are many applications of ML to scientific problems that look promising, visuals can be deceiving. Using numerical analysis techniques, we rigorously quantify the accura…
Learning continuous models for continuous physics
Aditi S. Krishnapriyan, Alejandro F. Queiruga, N. Benjamin Erichson +1
Dynamical systems that evolve continuously over time are ubiquitous throughout science and engineering. Machine learning (ML) provides data-driven approaches to model and predict t…
Stateful ODE-Nets using Basis Function Expansions
Alejandro Queiruga, N. Benjamin Erichson, Liam Hodgkinson +1
The recently-introduced class of ordinary differential equation networks (ODE-Nets) establishes a fruitful connection between deep learning and dynamical systems. In this work, we…
Continuous-in-Depth Neural Networks
Alejandro F. Queiruga, N. Benjamin Erichson, Dane Taylor +1
Recent work has attempted to interpret residual networks (ResNets) as one step of a forward Euler discretization of an ordinary differential equation, focusing mainly on syntactic…
Lipschitz Recurrent Neural Networks
N. Benjamin Erichson, Omri Azencot, Alejandro Queiruga +2
Viewing recurrent neural networks (RNNs) as continuous-time dynamical systems, we propose a recurrent unit that describes the hidden state's evolution with two parts: a well-unders…