Nature

A comparative machine and deep learning approach for predicting ultimate bearing capacity of shallow foundations in cohesionless soil

It evaluates a single, fixed set of hyperparameters for an LSTM model using k-fold cross-validation. While it saves the best-performing model from those cross-validation runs, it does not ...
GitHub

Ames Housing Regression Benchmark

This is a machine learning project built on the Ames Housing dataset, designed to show end-to-end regression workflow, model engineering, evaluation, reporting, and comparison. This project studies ...
The Lancet

AI-enabled forecasting of prehospital transfusion needs in patients with trauma: a multinational, registry-based, retrospective, machine learning development and validation study

aDepartment of Cardiology and Angiology, University Hospital Tübingen, Eberhard Karls University Tübingen, Tübingen, Germany bUniversity Department of Anesthesiology and Intensive Care Medicine, ...
Frontiers

Leveraging artificial intelligence for analysis of the gut microbiome for dementia diagnosis: a scoping review and discussion

Study designs (cross-sectional vs. longitudinal, observational study vs. experimental vs. mixed methods), country of participants, types of dementia studied (people with Alzheimer’s disease, mild ...
GitHub

GitHub - rohanmistry231/AI-From-Scratch: A unified hub for the Scratch Series — 200+ algorithms across ML, DL, NLP, LLM, GenAI, and TimeSeries, all implemented from scratch ...

AI From Scratch Every Algorithm. Implemented From Scratch. No Black Boxes. 200+ algorithms across 6 domains of artificial intelligence — all implemented from scratch using pure NumPy. No TensorFlow.