Siddhartha Chitrakar - Matrix Calculus and Usage in Machine Learning ml math скачать в хорошем качестве

Siddhartha Chitrakar - Matrix Calculus and Usage in Machine Learning ml math

ML relies on the fundamentals of linear algebra and calculus for optimization. This talk will review the intersection of both topics, Matrix Calculus, and the usage/importance of it in Machine Learning. While most often know each topic individually, in ML we leverage both fields to do high-dimensional optimization that is often missing in an undergraduate curriculum. We will briefly review the basics of these fundamentals, then explain how we can formally derive and solve high-dimensional optimization problems Siddhartha Chitrakar is a MSc. student at University of Alberta advised by Prof. Nidhi Hegde. He's interested in Trustworthy AI and how to leverage statistics to integrate societal factors like fairness and reliability. Currently, he focuses on quantifying how good predictions are (Uncertainty Quantification, Conformal Prediction) since if machine learning models are not confident, then admitting “I don’t know” is far safer than a wrong prediction. This session is brought to you by the Cohere Labs Open Science Community - a space where ML researchers, engineers, linguists, social scientists, and lifelong learners connect and collaborate with each other. We'd like to extend a special thank you to Katrina Lawrence and Neel Ghoshal, Leads of our ML Math group for their dedication in organizing this event. If you’re interested in sharing your work, we welcome you to join us! Simply fill out the form at https://forms.gle/ALND9i6KouEEpCnz6 to express your interest in becoming a speaker. Join the Cohere Labs Open Science Community to see a full list of upcoming events (https://tinyurl.com/CohereLabsCommuni....