machine learning

(8) rss icon
The latest research in training modern machine learning models: ‘A deterministic modification of gradient descent that avoids saddle points

Machine learning models, particularly those based on deep neural networks, have revolutionized the fields of data analysis, image recognition, and natural language processing. A key factor in the training of these models is the use of variants of gradient descent algorithms, which optimize model parameters by minimizing a loss function. However, the training optimization problem for neural networks is highly non-convex, presenting unique challenges.

Read more

New editor Q&A: Rhonda Righter of UC Berkeley

Rhonda Righter is joining the editorial board of the journal Probability in the Engineering and Informational Sciences. She brings with her a wealth of knowledge in the area of stochastic modelling and optimization; read her full biography here.…

Read more

Machine learning helps computers predict near-synonyms

Choosing the best word or phrase for a given context from among candidate near-synonyms, such as “slim” and “skinny”, is something that human writers, given some experience, do naturally; but for choices with this level of granularity, it can be a difficult selection problem for computers.…

Read more