6 papers
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…
A Kernel-based Resource-efficient Neural Surrogate for Multi-fidelity Prediction of Aerodynamic Field
Apurba Sarker, Reza T. Batley, Darshan Sarojini +1
Surrogate models provide fast alternatives to costly aerodynamic simulations and are extremely useful in design and optimization applications. This study proposes the use of a rece…
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…
KHRONOS: a Kernel-Based Neural Architecture for Rapid, Resource-Efficient Scientific Computation
Reza T. Batley, Sourav Saha
Contemporary models of high dimensional physical systems are constrained by the curse of dimensionality and a reliance on dense data. We introduce KHRONOS (Kernel Expansion Hierarc…