EECS Special Seminar: Vikash Mansinghka, "Engineering intelligent systems via probabilistic computation" - March 30 at 11:00 am

Speaker: Vikash Mansinghka , MIT

Date: Tuesday, March 30, 2021

Time: 11:00 AM to 12:00 PM Note: all times are in the Eastern Time Zone

Public: No

Location: Virtual - TBD

Event Type: Seminar

Room Description:

Host: Armando Solar-Lezama, CSAIL MIT

Contact: Sally O. Lee, 3-6837,

Relevant URL:

Speaker URL: None

Speaker Photo:

Reminders to:

Reminder Subject: TALK: EECS Special Seminar: Vikash Mansinghka, "Engineering intelligent systems via probabilistic computation" - March 30 at 11:00 am


The data efficiency, flexibility, robustness, and energy efficiency of
human intelligence have yet to be matched by AI systems. How can we
narrow these gaps between artificial and natural intelligence? This
talk will review progress towards solving these problems drawing on
probabilistic computation, an emerging paradigm that integrates
generative models, probabilistic inference, and Monte Carlo into the
building blocks of software and hardware. Rather than represent
complex probability distributions explicitly, via factorization of
density functions, probabilistic computing systems represent them
implicitly, via generative programs that model the causal processes
unfolding in the external world and inside intelligent systems. Rather
than calculate exact probabilities for inference, probabilistic
computing systems sample informed guesses, via massively parallel,
online inference programs that combine sequential Monte Carlo,
stochastic gradient descent, and variational inference with deep
learning and symbolic reasoning. I will illustrate these principles
using Gen, a new, multi-paradigm AI programming platform developed by
my group, that integrates probabilistic, symbolic, and differentiable
approaches to deliver state-of-the-art performance. Examples will be
drawn from models of core computations from common-sense scene
understanding --- such as inferring peoples’ probable goals from noisy
observations of their motion, and perceiving the 3D structure of the
world --- as well as the problem of learning the structure of
generative programs from limited data. I will also briefly review
stochastic digital hardware designs, as well as domain-specific
probabilistic programming languages that deliver competitive
performance and accuracy on large-scale real-world applications.


Vikash Mansinghka is a Principal Research Scientist at the MIT Brain &
Cognitive Sciences Department and Quest for Intelligence, where he
leads the 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 Brain &
Cognitive Sciences Department. 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 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.

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Sally O. Lee Email at Monday, March 22, 2021 at 8:28 AM.