7 papers
Separable Neural Architectures as Physical World Models: from Mathematical Theory to Applications
Reza T Batley, Andrew Kichline, Sourav Saha
This work introduces the Separable Neural Architecture (SNA), a function representational class combining neural approximation with tensor decomposition. The SNA decouples localize…
Separable neural architectures as a primitive for unified predictive and generative intelligence
Reza T. Batley, Apurba Sarker, Rajib Mostakim +2
Intelligent systems across physics, language and perception often exhibit factorisable structure, yet are typically modelled by monolithic neural architectures that do not explicit…
Agile Reinforcement Learning through Separable Neural Architecture and Applications
Rajib Mostakim, Reza T. Batley, Sourav Saha
Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet go-to function approximators - multilayer perceptrons (MLPs) - are often paramet…
Leviathan: Decoupling Input and Output Representations in Language Models
Reza T. Batley, Sourav Saha
Modern language models use a single matrix for input embedding and output projection. This couples two distinct objectives: token representation and discrimination over a vocabular…
A Unified Generative-Predictive Framework for Deterministic Inverse Design
Reza T. Batley, Sourav Saha
Inverse design of heterogeneous material microstructures is a fundamentally ill-posed and famously computationally expensive problem. This is exacerbated by the high-dimensional de…
The Method of Infinite Descent
Reza T. Batley, Sourav Saha
Training - the optimisation of complex models - is traditionally performed through small, local, iterative updates [D. E. Rumelhart, G. E. Hinton, R. J. Williams, Nature 323, 533-5…
Explainable Hierarchical Deep Learning Neural Networks (Ex-HiDeNN)
Reza T. Batley, Chanwook Park, Wing Kam Liu +1
Data-driven science and computation have advanced immensely to construct complex functional relationships using trainable parameters. However, efficiently discovering interpretable…