New AI framework autonomously optimizes training data, architectures and algorithms — outperforming human baselines

EVOLVE, an agentic framework that autonomously optimizes AI training data, model architectures, and learning algorithms — ...
Frontiers

Brain-inspired learning and adaptation in large models

Recent advances in large-scale AI models, including large language and vision-language-action models, have significantly expanded the capabilities of ...
Hosted on MSN

AI ensemble models sharpen NBA game predictions and strategy

New research using AI-powered stacked ensemble models has improved accuracy in predicting NBA game results by combining multiple machine learning algorithms. These models not only forecast outcomes ...
IEEE

Sentiment Analysis Algorithm Based on Deep Transfer Learning for Multi-Source Data Fusion

Abstract: To tackle the challenge of data diversity in sentiment analysis and improve the accuracy and generalization ability of sentiment analysis, this study first cleans, denoises, and standardizes ...
IEEE

BDAFL: A Blockchain-Integrated Decentralized Asynchronous Federated Learning Algorithm in Industrial Internet

Abstract: With the rapid development of the industrial Internet, the value of internal data is increasing. Federated learning, which can protect data privacy, is crucial in this context. However, it ...