![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Austin Tripp and Shoaib Siddiqui, University of Cambridge.
Wednesday 26 October 2022, 11:00-12:30
Cambridge University Engineering Department, CBL Seminar room BE4-38
Contact: No managers listed
0 upcoming talks View 25 archived talks
Machine Learning Reading Group @ CUED
Benchmarking and evaluation in contemporary machine learning
Machine Learning Reading Group @ CUED
Advanced artificial agents intervene in the provision of reward
Machine Learning Reading Group @ CUED
Theory and Practice of Infinitely Wide Neural Networks - Guest Talk
Machine Learning Reading Group @ CUED
The unreasonable effectiveness of mathematics in large scale deep learning
Machine Learning Reading Group @ CUED
The role of meta-learning for few-shot classification
Machine Learning Reading Group @ CUED
Benefits and Shortcomings of Assistance
Machine Learning Reading Group @ CUED
Discussion: Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
Machine Learning Reading Group @ CUED
Discussion: Learning PAC-Bayes Priors for Probabilistic Neural Networks
Machine Learning Reading Group @ CUED
Rethinking evaluation for machine learning models
Machine Learning Reading Group @ CUED
Discussion: Bayesian Model Selection, the Marginal Likelihood, and Generalization
Machine Learning Reading Group @ CUED
How close are these distributions? A brief introduction to statistical distances and divergences.
Machine Learning Reading Group @ CUED
Bests of ICLR
Machine Learning Reading Group @ CUED
Machine Learning with Quantum Computers
Machine Learning Reading Group @ CUED
Autoregressive Diffusion Models
Machine Learning Reading Group @ CUED
An Overview of AI Alignment
Machine Learning Reading Group @ CUED
The Bayesian Learning Rule for Adaptive AI
Engineering Safe AI
Ambitious Value Learning
Engineering Safe AI
Machine Theory of Mind
Engineering Safe AI
Embedded Agency
Engineering Safe AI
Comprehensive AI Services
Engineering Safe AI
Incomplete Contracting and AI Alignment
Engineering Safe AI
The Algorithmic Foundations of Differential Privacy (Chapters 1 and 2)
Engineering Safe AI
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning
Engineering Safe AI
Measuring and avoiding side effects using relative reachability
Cambridge Big Data
Harnessing AI and Robotics for Materials Discovery
Please see above for contact details for this list.