At this week’s lab meeting, Vikash Mansighka will give a talk titled “Scaling towards human-like AI via probabilistic programming.”
- Tuesday, November 23, 16:00–17:00 (Montreal time, UTC-5). <– Note the time! This meeting is 1 hour later than usual.
- Meetings are via Zoom. If you would like to attend the talk but have not yet signed up for the MCQLL meetings this semester, please send an email to firstname.lastname@example.org.
A great deal of enthusiasm has been focused on building increasingly large neural models. We believe it is now possible to pursue an alternate scaling roadmap based on probabilistic programming, to build AI systems that actually see, learn and think like people, with more human-like flexibility, data efficiency, robustness, and generalizability. The probabilistic source code for these AI systems is partly written by AI engineers and partly learned from data. This approach integrates the best of large-scale generative modeling and deep learning with probabilistic inference and symbolic programming. Unlike neural networks, probabilistic programs can report what they know and what they don’t; they model the world in terms of explainable, human-editable representations; they can be modularly trained & tested; and they can learn new symbolic code rapidly and accurately from sparse data. This talk will introduce basic concepts in probabilistic programming, and survey AI applications where probabilistic programming has recently outperformed machine learning:
It will also briefly review larger MIT efforts to apply probabilistic programming to reverse-engineer human common sense, to engineer data-driven expert systems, and to scale to low-power, biologically plausible hardware implementations of probabilistic programming, via massively parallel circuits of stochastic spiking neurons.
- 3D object & scene perception from cluttered indoor video, improving accuracy and robustness over deep learning
- common-sense deduplication, linkage, and cleaning of databases with millions of records
- automated model discovery for multivariate data streams
Vikash Mansinghka is a Principal Research Scientist at MIT, where he leads the MIT Probabilistic Computing Project. Vikash holds S.B. degrees in Mathematics and in Computer Science from MIT, as well as an M.Eng. in Computer Science and a PhD in Computation from the Department of Brain & Cognitive Sciences. He also held graduate fellowships from the National Science Foundation and MIT’s Lincoln Laboratory. His PhD dissertation on natively probabilistic computation won the MIT George M. Sprowls dissertation award in computer science, and his research on the Picture probabilistic programming language won an award at CVPR. He co-founded three VC-backed startups: Prior Knowledge (acquired by Salesforce in 2012) and Empirical Systems (acquired by Tableau in 2018), and Common Sense Machines (founded in 2020). He has also advised DeepMind and Intel on AI research, and helped leading companies in banking, insurance, IT, pharma, and healthcare apply open-source software implementing his lab’s research. He served on DARPA’s Information Science and Technology advisory board from 2010-2012, currently serves as an action editor for the Journal of Machine Learning Research, and co-founded the International Conference on Probabilistic Programming.