The Michigan Student Artificial Intelligence Lab (MSAIL) is a student organization for discussion of artificial intelligence and machine learning. Andrew Ng said:
“ ...if you read research papers consistently, if you seriously study half a dozen papers a week and you do that for two years, after those two years you will have learned a lot... But that sort of investment, if you spend a whole Saturday studying rather than watching TV, there's no one there to pat you on the back or tell you you did a good job. ” — Andrew NgMSAIL is a community in which motivated students can read and discuss modern machine learning literature together. We welcome students of all backgrounds and ability. To join MSAIL and stay up to date, simply join our Slack team! Also be sure to check out our sister organization: the Michigan Data Science Team! We are both graciously sponsored by the Michigan Institute for Data Science.
Robots often need haptic (touch) and visual feedback to perform tasks where they manipulate objects in their environments. The authors of this paper explore ways to learn a strategy to control a robot from combined representations of these data, using self-supervised and deep reinforcement learning.
Isolation of cases and contact tracing has been used to control the outbreaks of COVID-19. Whether this strategy works depends on characteristics of both the pathogen and the response. This week we analyzed and discussed a mathematical model to assess if isolation and contract tracing are effective in stopping this virus.
A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective with the hope that representations useful for subsequent tasks will arise as a side effect. This week we discussed a paper that proposes directly targeting later desired tasks by meta-learning an unsupervised learning rule that will later be useful for those tasks.