September 21, 2018 - 4:00 pm
Eric Shea-Brown, University of Washington
Abstract: There is an avalanche of new data on the brain’s activity, revealing the collective dynamics of vast numbers of neurons. In principle, these collective dynamics can be of almost arbitrarily high dimension, with many independent degrees of freedom — and this may reflect...
July 24, 2018 - 11:00 am
Dr. Joseph T. Lizier, The University of Sydney
Abstract:
The space-time dynamics of interactions in neural systems are often described using terminology of information processing, or computation, in particular with reference to information being stored, transferred and modified in these systems. In this talk, we describe an information-...
The space-time dynamics of interactions in neural systems are often described using terminology of information processing, or computation, in particular with reference to information being stored, transferred and modified in these systems. In this talk, we describe an information-...
July 2, 2018 - 4:00 pm
Prof. Lior Wolf, Tel Aviv University and Facebook AI Research
Abstract: Generative models are constantly improving, thanks to recent contributions in adversarial training, unsupervised learning, and autoregressive models. In this talk, I will describe new generative models in computer vision, voice synthesis, and music.
In music – I will...
In music – I will...
May 21, 2018 - 4:00 pm
Jonathan Miller, Associate Professor | Physics and Biology Unit, Okinawa Institute of Science and Technology...
Abstract: By a quirk of evolution, camouflaging octopus and cuttlefish report their visual perceptions by modulating their skin color and 3-d texture on time scales of seconds or minutes to match their surroundings (they are generative image modelers). Their survival demands that predators...
May 4, 2018 - 2:00 pm
Jon Shlens, Google Brain
Abstract:
Recent advances in machine learning have profoundly influenced our study of computer vision. Successes in this field have demonstrated the expressive power of learning representations directly from visual imagery — both in terms of practical utility and unexpected expressive abilities. In...
Recent advances in machine learning have profoundly influenced our study of computer vision. Successes in this field have demonstrated the expressive power of learning representations directly from visual imagery — both in terms of practical utility and unexpected expressive abilities. In...
April 20, 2018 - 4:00 pm
Phil Nelson, Google Research | Google Accelerated Science team
Abstract: Google Accelerated Sciences is a translational research team that brings Google's technological expertise to the scientific community. Recent advances in machine learning have delivered incredible results in consumer applications (e.g. photo recognition, language translation), and is now...
April 18, 2018 - 2:00 pm
Mikhail Belkin, Ohio State University
Abstract:
A striking feature of modern supervised machine learning is its pervasive over-parametrization. Deep networks contain millions of parameters, often exceeding the number of data points by orders of magnitude. These networks are trained to nearly interpolate the data by driving the training...
A striking feature of modern supervised machine learning is its pervasive over-parametrization. Deep networks contain millions of parameters, often exceeding the number of data points by orders of magnitude. These networks are trained to nearly interpolate the data by driving the training...
April 13, 2018 - 4:30 pm
Christof Koch, CBMM EAC member, Allen Institute for Brain Science
Abstract:
Rapid advances in convolutional networks and other machine learning techniques, in combination with large data bases and the relentless hardware advances due to Moore’s Law, have brought us closer to the day when we will be able to have extended conversations with programmable systems,...
Rapid advances in convolutional networks and other machine learning techniques, in combination with large data bases and the relentless hardware advances due to Moore’s Law, have brought us closer to the day when we will be able to have extended conversations with programmable systems,...
April 12, 2018 - 4:30 pm
Marge Livingstone, CBMM, Harvard Medical
Host: Tomaso Poggio
This talk is open to the CBMM Community only
This talk is open to the CBMM Community only
February 16, 2018 - 4:00 pm
Ann M. Hermundstad, PhD, Janelia Research Campus
Abstract: The brain exploits the statistical regularities of the natural world. In the visual system, an efficient representation of light intensity begins in retina, where statistical redundancies are removed via spatiotemporal decorrelation. Much less is known, however, about the efficient...
December 15, 2017 - 4:30 pm
Jeff Hawkins, Co-Founder, Numenta
Please note the change in start time. This talk will be starting at 4:30pm, on Friday, Dec. 15, 2017.
Abstract: In this talk I will describe a theory that sensory regions of the neocortex process two inputs. One input is the well-known sensory data arriving via thalamic relay cells. We propose...
Abstract: In this talk I will describe a theory that sensory regions of the neocortex process two inputs. One input is the well-known sensory data arriving via thalamic relay cells. We propose...
November 17, 2017 - 2:00 pm
Klaus-Robert Müller, Technische Universität Berlin
Abstract: In recent years, machine learning (ML) and artificial intelligence (AI) methods have begun to play a more and more enabling role in the sciences and in industry. In particular, the advent of large and/or complex data corpora has given rise to new technological challenges and possibilities...
November 3, 2017 - 4:00 pm
McGovern Seminar Room (46-3189)
Ryan Cotterell
Title: Probabilistic Typology: Deep Generative Models of Vowel Inventories
Abstract: Linguistic typology studies the range of structures present in human language. The main goal of the field is to discover which sets of possible phenomena are universal, and which are merely frequent. For example,...
Abstract: Linguistic typology studies the range of structures present in human language. The main goal of the field is to discover which sets of possible phenomena are universal, and which are merely frequent. For example,...
September 15, 2017 - 2:00 pm
Dr. David Ferrucci
Abstract: AI systems should not only propose solutions or answers but also explain why they make sense. Statistical machine learning is a powerful tool for discovering patterns in data, but, Dr. Ferrucci asks, can it produce understanding or enable humans to justify and take reasoned responsibility...
May 26, 2017 - 4:00 pm
Kevin Murphy (Google Research)
Host: Josh Tenenbaum
Abstract: In this talk, I summarize some recent work in my group related to visual scene understanding and "grounded" language understanding. In particular, I discuss the following topics:
Our DeepLab system for semantic segmentation (PAMI'17, https://arxiv.org/abs/1606.00915).
Our object detection...
Our DeepLab system for semantic segmentation (PAMI'17, https://arxiv.org/abs/1606.00915).
Our object detection...