معرفی
Roger Grosse is an Associate Professor of Computer Science at the University of Toronto and holds the Schwartz Reisman Chair in Technology and Society. He is a founding member of the Vector Institute and serves on the Alignment Science Team at Anthropic. His research focuses on understanding neural network training dynamics, improving training efficiency, and ensuring AI alignment with human values.
Education: BS in Symbolic Systems (Stanford, 2008), MS (Stanford, 2009), and PhD in Computer Science (MIT, 2014) under Bill Freeman and Josh Tenenbaum. Postdoc at University of Toronto (2014-2016) with Ruslan Salakhutdinov.
Research Interests: Investigates how neural networks learn, detects mesa-optimizers, and develops methods to ensure AI safety. Specific areas include tracing AI behaviors to training data, generalization patterns, and inner objective reverse engineering.
Awards: Sloan Fellowship, Canada Research Chair, and Canada CIFAR AI Chair.
Courses taught include Neural Networks and Deep Learning (CSC413/2516), AI Alignment (CSC2547), and Machine Learning fundamentals (CSC311).
Co-created Metacademy, an educational platform using dependency graphs for personalized machine learning learning plans.
