Microsoft

Rethinking Machine Learning Collective Communication as a Multi Commodity Flow problem

Cloud operators utilize collective communication optimizers to enhance the efficiency of the single-tenant, centrally managed training clusters they manage. However, current optimizers struggle to ...
IEEE

Analysis & Modeling of Deep Learning Techniques for Flowchart to Code Generation

Abstract: This research basically explores the analysis and modelling of deep learning techniques. Advanced AI is being integrated and to automate the flowchart-to-code generation process, vision ...
Nature

Omics with active learning optimizes phenotypic screens

Phenotypic drug discovery screens offer physiologically relevant disease-linked readouts and account for polypharmacology. However, they are more complex than target-based screens and difficult to ...
Phys.org

Interpretable machine learning to accelerate nanocatalyst discovery

A fast and accurate surrogate model screens over 10,000 possible metal-oxide supports for a platinum nanocatalyst to prevent sintering under high temperatures. Metal nanoparticles catalyze reactions ...
Nanowerk

Machine learning speeds platinum nanocatalyst discovery and stops high temperature sintering

A fast and accurate surrogate model screens over 10,000 possible metal-oxide supports for a platinum nanocatalyst to prevent sintering under high temperatures. “As particles grow in size, they hide ...
IEEE

Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning

Abstract: This paper presents an image-based framework for classifying fluid flow regimes into low and high-speed states by utilizing spatially localized texture features combined with machine ...