Nature

AIs are biased toward some Indian castes — how can researchers fix this?

Benchmarks reveal how artificial-intelligence systems reinforce discriminatory social hierarchies.
Nature

Machine learning articles from across Nature Portfolio

Machine learning is the ability of a machine to improve its performance based on previous results. Machine learning methods enable computers to learn without being explicitly programmed and have ...
IEEE

Hierarchical and Bidirectional Contrastive Learning for Hyperspectral Image Classification

Abstract: Representing hyperspectral images (HSIs) is a complex and challenging task, primarily due to spectral uncertainty. The learnable prototypical contrastive learning is specialized in ...
IEEE

Soft Neighbors Supported Contrastive Clustering

Abstract: Existing deep clustering methods leverage contrastive or non-contrastive learning to facilitate downstream tasks. Most contrastive-based methods typically learn representations by comparing ...
GitHub

Reinforcement Learning in LLM Tutorial (Python)

Here I show you reinforcement learning (RL) examples to train (fine-tune) language models (LM). All these examples are implemented from scratch (manually) in a step-by-step manner (*1), and also shows ...
GitHub

[ICML 2025] Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection

The figures below illustrate the overview pipeline and components of the CAROTS framework. For more detailed information, please refer to our paper.