News

Study uses machine learning to map pH-dependent performance of tin catalysts
Some of the most encouraging results for reaction-enhancing catalysts come from one material in particular: tin (Sn). While ...
Exploring interpretable machine learning
I am a computational biologist interested in interpretable machine learning for genomics and health care. Interpretable ...
InfoWorld1d
AWS adds incremental and distributed training to Clean Rooms for scalable ML collaboration
The new capabilities are designed to enable enterprises in regulated industries to securely build and refine machine learning ...
Novel model optimization algorithm improves robustness of near-infrared spectroscopy models
A research team from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has proposed a novel model optimization algorithm—External Calibration-Assisted Screening (ECA)— that ...
IEEE2d
Research on the Application of Gradient Descent Algorithm in Machine Learning - IEEE Xplore
The gradient descent algorithm is a type of optimization algorithm that is widely used to solve machine learning algorithm model parameters. Through continuous iteration, it obtains the gradient of ...
The Manila Times3d
Xingwen Guo is Blending Finance and AI to Form a New Approach to Financial Management
A new approach to financial risk management combines ensemble machine learning algorithms with traditional financial theory to enhance systemic risk prediction. By integrating data-driven modeling ...
Global Times3d
Chinese cities roll out AI curriculum in schools, linking learning outcomes to student evaluation
The regulation also requires students to learn how to use common data labeling tools, solve issues like incomplete or inaccurate data, understand key machine learning algorithms such as classification ...
IEEE4d
Enhancing Malware Detection Using Machine Learning: A Comparative Study of Classification Algorithms - IEEE Xplore
This research investigates the efficacy of various machine learning algorithms in detecting malware. Utilizing a dataset of 20,000 observations with 33 features,28 classification algorithms are ...