Santa Fe Institute

A simple baseline for AI forecasting in machine learning

In a recent paper, SFI Complexity Postdoctoral Fellow Yuanzhao Zhang and co-author William Gilpin show that a deceptively ...
Tech Xplore

Compression technique makes AI models leaner and faster while they're still learning

Training a large artificial intelligence model is expensive, not just in dollars, but in time, energy, and computational ...
Frontiers

Semi-Supervised Learning with Foundation Models for Biomedical Data Analysis: Multimodality, Generative AI, and Clinical Adaptation

Biomedical data analysis has evolved rapidly from convolutional neural network-based systems toward transformer architectures and large-scale foundation ...
Frontiers

The Neuro Bureau Preprocessing Initiative: open sharing of preprocessed neuroimaging data and derivatives

Grass-roots initiatives such as the 1000 Functional Connectomes Project (FCP) and International Neuroimaging Data- sharing Initiative (INDI) [1] are successfully amassing and sharing large-scale brain ...
IEEE

Machine Learning Models Tailored to Resource-Constrained Environments, with a Focus on Data Preprocessing Techniques

Abstract: In the era of pervasive computing, machine learning (ML) is increasingly deployed on resource-constrained devices, such as smartphones, IoT devices, and edge nodes. This research explores ML ...
IEEE

Data Driven Mental Health Predicting Depression Using Machine Learning

Abstract: The rise of information investigation methods such as machine learning is opening up unused openings in the field of mental wellbeing. This department of inquire about, known as data-driven ...