I am an Assistant Professor of Statistics at the University of Wisconsin-Madison focusing on deep learning and machine learning research. Among others, I am also contributor to open source software and author of the bestselling book Python Machine Learning. — Lees op sebastianraschka.com/blog/2021/dl-course.html
Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these models are generally not interpretable to users. In various domains, such as healthcare, finance, or law, it Read more
Large-scale pretrained transformers learn from corpuses containing oceans of factual knowledge, and are surprisingly good at recalling this knowledge without any fine-tuning. In a new paper, a team from Microsoft Research and Peking University peeps into pretrained transformers, proposing a method to identify the “knowledge neurons” responsible for storing this Read more
Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks — Lees op arxiv.org/abs/1807.01969
Gaussian multiplicative noise is commonly used as a stochastic regularisation technique in training of deterministic neural networks. A recent paper reinterpreted the technique as a specific algorithm for approximate inference in Bayesian neural networks; several extensions ensued. — Lees op arxiv.org/abs/1711.02989
Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop Read more