Home Page Spotlights
Computer models that mimic humans’ extraordinary hearing abilities could improve treatments for hearing loss. MIT neuroscientist Josh McDermott hopes to develop computational models that can perform sophisticated auditory tasks as well as the human brain.
Prof. Poggio will give a talk at the Bower Award for Neural Networks for Machine Learning symposium honoring Kunihiko Fukushima on April 28, 2021 at 9:00AM ET. Click to see full list of speakers and register for the webinar.
Memory permits the reuse of past cognitive computations. Work by CBMM's Dasgupta and Gershman have suggested that memory may be much more ubiquitous, permeating many other computational systems.
This new book introduces the neuroscientific study of neuronal computations in visual cortex alongside of the psychological understanding of visual cognition and the burgeoning field of biologically-inspired artificial intelligence.
CBMM's Director Tomaso Poggio has been selected as a panelist for the upcoming webinar series on March 24, 2021 hosted by the Italian Embassy and partnering with the National Science Foundation exploring artificial inteligence.
AI Week TLV, a five-day international event this February with the experts who are reshaping AI innovation, announced their speaker list including CBMM's Tomaso Poggio and Shimon Ullman.
IBM-MIT collaboration announces a challenge for the computer vision community to develop robust models for object recognition, demonstrating accurate predictions on ObjectNet images.
The Center for Brains, Minds and Machines is well-represented at the thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020).
Figure 1: Typical double descent of the condition number (y axis) of a random data matrixdistributed asN(0,1): the condition number is worse whenn=d, better ifn > d(on the rightofn=d) and also better ifn < d(on the left ofn=d).
An artificial intelligence (AI) network developed by Google AI offshoot DeepMind has made a gargantuan leap in solving one of biology’s grandest challenges — determining a protein’s 3D shape from its amino-acid sequence.
Advances in Cognitive Systems announces a memorial symposium in honor of the 2019 Herbert A. Simon Prize for Advances in Cognitive Systems winner Patrick Henry Winston.
Recent advances give theoretical insight into why deep learning networks are successful. CBMM Director Tomaso Poggio, postdoc Andrzej Banburski and graduate student Qianli Liao look into the "black box" of deep learning to provide insights.
The RSS Keynote on July 15 was delivered by Josh Tenenbaum, Professor of Computational Cognitive Science at MIT BCS, CSAIL. Titled “It’s all in your head: Intuitive physics, planning, and problem-solving in brains, minds and machines”.
Looking for something good to watch tonight? Netflix has released "Babies: Part 2" which includes CBMM PIs Rebecca Saxe, MIT (P2:E1 What Babies Know) and Laura Schulz, MIT (P2:E6 Toddlers).
In CBMM Memo 105, CBMM researchers solve the generalization issues by teaching the network using simple curves before seeing the most complex ones, which facilitates learning the “coloring routine”.