News

AI Collaborative Learning: Understanding Deep Learning Chapter 7 - The Dual Art of Backpropagation and Initialization in AI's 'Neural Hub'

In the previous chapter, we learned various strategies to guide AI models 'down the mountain' (optimization algorithms), such ...
Hackaday

Understanding Deep Learning: Free MIT Press EBook For Instructors And Students

The recently published book Understanding Deep Learning by [Simon J. D. Prince] is notable not only for focusing primarily on the concepts behind Deep Learning — which should make it highly accessible ...

Baidu Open Sources ERNIE-4.5-21B-A3B-Thinking Model, Opening a New Chapter in Long Text Reasoning

At the WAVESUMMIT Deep Learning Developer Conference in 2025, Baidu officially announced the open-source release of its latest ERNIE-4.5-21B-A3B-Thinking model, which instantly sparked widespread ...
Phys.org

Using geometry and physics to explain feature learning in deep neural networks

Deep neural networks (DNNs), the machine learning algorithms underpinning the functioning of large language models (LLMs) and other artificial intelligence (AI) models, learn to make accurate ...
AZoCleantech on MSN

Deep Learning Revolutionizes Biodiesel Production

The integration of deep learning in biodiesel research accelerates feedstock evaluation and optimizes production, making it ...
The Chosun Ilbo on MSN

Microsoft model outperforms DeepSeek R1 with 1/50th parameters

Microsoft, MS, which unveiled an artificial intelligence (AI) paper late last month, has drawn attention in the industry. The ...
JSTOR Daily

On Nearly Assumption-Free Tests of Nominal Confidence Interval Coverage for Causal Parameters Estimated by Machine Learning

Statistical Science, Vol. 35, No. 3, Special Issue on Causal Inference (August 2020), pp. 518-539 (22 pages) For many causal effect parameters of interest, doubly robust machine learning (DRML) ...