BIOENGINEER

Stacked machine learning model predicts concrete strength with high accuracy

A hybrid stacking ensemble of XGBoost, LightGBM and CatBoost with domain-informed features predicts concrete compressive ...
BIOENGINEER

Pathway Epigenetic Model Uncovers Cross-Tissue DNA Methylation Patterns Linked to Asthma

A cross-tissue machine learning framework utilizing Gene Ontology pathway-level DNA methylation scores accurately identified ...

Direct Manipulation of Neural Networks via Weight-Space Programming: The Dawn and Ripples of Self-Reorganizing AI Demonstrated by GPT-6 Astra

Box ManipulationIn the history of artificial intelligence and machine learning, the determination of internal parameters ...
xenospectrum

MIT Shows an LLM Can Read and Edit Another Neural Network's Weights Directly

MIT CSAIL's "weight-space programming" has a frontier LLM read and edit neural network weights directly, with no gradient descent. Surgical edits ended Qwen's reasoning loops, but the results come ...
GitHub

Neural Networks and Deep Learning

B.E. CSE at Osmania University (2014-2018) and M.Tech CS / AI at SSSIHL. - saikrishnavadali05/Academic-CSE-Osmania-SSSIHL ...
GitHub

Hospital Readmission Prediction System

A production-ready, end-to-end Machine Learning and Healthcare Data Science project to predict 30-day hospital readmissions, understand patient risk trajectories, and empower clinical teams with ...
Science

Structural bias enables reliable sim-to-real transfer in reinforcement learning for robot swarms

Constraining policies to select behavior modules allows reinforcement learning transfer from simulation to real robot swarms.