Home Page Spotlights

Gadi Geiger
Not having a college degree didn’t stop Gadi Geiger from becoming a neuroscientist—or serving as the go-to guy for career advice in the Poggio Lab.
Whether, and to what extent, what is learned in the college classroom (if left unused) is likely to be mostly forgotten a “few” years after graduation. How this work can influence practical learning engineering at scale, with examples from Kaplan.
We brought together AI researchers, entrepreneurs, and thought leaders for our second Beneficial AI Conference, held in Asilomar, California. Speakers and panelists discussed the future of AI, economic impacts, legal issues, ethics, and more...
Speech representation, perception and recognition workshop
The focus of the workshop is on the computations and learning involved in human speech understanding that are required for speech-enabled machines, following CBMM’s mission to understand intelligence in brains and replicate it in machines.
Interaction with the world requires an organism to transform sensory signals into representations in which behaviorally meaningful properties of the environment are made explicit. These representations are derived through cascades of neuronal ...
The Trolley Problem
Daniel Rockmore - Professor of Mathematics, William H. Neukom 1964 Distinguished Professor of Computational Science, Director of the Neukom Institute for Computational Science, Dartmouth College - discusses, how do we program moral philosophy and values?
CBMM Logo
Humans are remarkably adept at interpreting the gaze direction of other individuals in their surroundings. This skill is at the core of the ability to engage in joint visual attention, which is essential for establishing social interactions. ...
Figure 1 from CBMM Memo No. 58
The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. ...
Science Supplement Dec. 16, 2016
[December 16, 2016] Read Prof. Tomaso Poggio's article in the lastest Supplement to Science - Brain-Inspired intelligent robotics: The intersection of robotics and neuroscience - discussing the integral part multiple disciplines working together.
CBMM Logo
We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and (2) recurrent learning.
CBMM logo
Why are human inferences sometimes remarkably close to the Bayesian ideal and other times systematically biased? One notable instance of this discrepancy is that tasks where the candidate hypotheses are explicitly available result ...
Sestri Levante, Italy - photo: Kris Brewer
Recordings of the lectures from June 2016's BMM Workshop in Sestri Levante, Italy are now being uploaded to the website. Eight (8) videos are available now with more coming soon.
CBMM logo
We present a study on two key characteristics of human syntactic annotations: anchoring and agreement.
Prof. Winrich Freiwald wins Columbia University’s 2016 W. Alden Spencer Award
The prize, given by Columbia University, recognizes outstanding research contributions in the field of neuroscience.

Pages