Machine learning methodologies encompass algorithmic frameworks and architectures for training, optimizing, and deploying models such as neural networks, transformers, diffusion models, and reinforcement learning agents. Work in this area develops new training objectives, curriculum schemes, speculative and efficient decoding, pruning and communication-reduction strategies, and biologically inspired or physics-informed architectures. The domain also includes safety preservation, unlearning, scaling laws, and specialized methods for vision, language, control, and scientific computing, aiming to improve performance, efficiency, robustness, and controllability of complex AI systems.
Computer Sciences
Researchers have demonstrated a new training technique that significantly improves the accuracy of graph neural networks (GNNs)—AI systems used in applications from drug discovery to weather forecasting. GNNs are AI systems ...
Apr 13, 2026
0
11
Computer Sciences
There is an exciting future on the horizon—one in which your thoughts could directly control electronic devices you use every day. In many ways, that future is already here, enabled by neural interfaces—engineered devices ...
Apr 12, 2026
0
21
Computer Sciences
In a recent paper, SFI Complexity Postdoctoral Fellow Yuanzhao Zhang and co-author William Gilpin show that a deceptively simple forecasting strategy can outperform several leading machine learning forecasting models.
Apr 10, 2026
0
8
Computer Sciences
Training a large artificial intelligence model is expensive, not just in dollars, but in time, energy, and computational resources. Traditionally, obtaining a smaller, faster model either requires training a massive one first ...
Apr 9, 2026
0
38
Computer Sciences
Researchers at Skoltech have proposed a new approach to training neural networks for wave propagation in absorbing media. The method significantly improves the accuracy and stability of solutions and accelerates model training ...
Apr 7, 2026
0
9
Software
Data centers consume millions of homes' worth of electricity each year, with much of that electricity simply powering the cooling systems that keep the facilities operational. Researchers at Penn State are addressing this ...
Apr 7, 2026
0
9
Computer Sciences
One of the most influential scientific and philosophical viewpoints is "More is Different," introduced in 1972 by Nobel Prize–winning physicist Philip W. Anderson, highlighting the limitations of the reductionist approach. ...
Apr 3, 2026
0
22
Hi Tech & Innovation
A research team at Tohoku University and Future University Hakodate has demonstrated that living biological neurons can be trained to perform a supervised temporal pattern learning task previously carried out by artificial ...
Apr 3, 2026
0
21
Computer Sciences
Although AI is not intentionally biased, it can inherit biases from the data fed into it, learning and repeating them until the system becomes inherently unfair. This is complicated by the problem of identifying where the ...
Apr 2, 2026
0
11
Security
From smartphone facial recognition to autonomous vehicles, artificial intelligence (AI) has long been protected as a black box. However, a joint research team from KAIST and international institutions has uncovered a new ...
Apr 1, 2026
0
21
