...

Upcoming Seminar

...

Energy-efficient neuromorphic hardware and its use for deep neural networks

Date: Feb. 14, 2pm

Speaker: Steve Esser (IBM)

...

Abstract: Neuromorphic computing draws inspiration from the brain's structure to create energy-efficient hardware for running neural networks.  Pursuing this vision, we created the TrueNorth chip, which embodies 1 million neurons and 256 million configurable synapses in contemporary silicon technology, and runs using under 100 milliwatts.  Spiking neurons, low-precision synapses and constrained connectivity are key design factors in achieving chip efficiency, though they stand in contrast to today's conventional neural networks that use high precision neurons and synapses and have unrestricted connectivity.  Conventional networks are trained today using deep learning, a field developed independent of neuromorphic computing, and are able to achieve human-level performance on a broad spectrum of recognition tasks.  Until recently, it was unclear whether the constraints of energy-efficient neuromorphic computing were compatible with networks created through deep learning.  Taking on this challenge, we demonstrated that relatively minor modifications to deep learning methods allows for the creation of high performing networks that can run on the TrueNorth chip.  The approach was demonstrated on 8 standard datasets encompassing vision and speech, where near state-of-the-art performance was achieved while maintaining the hardware's underlying energy-efficiency to run at > 6000 frames / sec / watt.  In this talk, I will present an overview of the TrueNorth chip, our methods to train networks for this chip and a selection of performance results.

...

ProxImaL: Efficient Image Optimization using Proximal Algorithms

Date: Feb. 28, 2pm

Speaker: Felix Heide

...

ProxImaL is a domain-specific language and compiler for image optimization problems that makes it easy to experiment with different problem formulations and algorithm choices. The language uses proximal operators as the fundamental building blocks of a variety of linear and nonlinear image formation models and cost functions, advanced image priors, and different noise models. The compiler intelligently chooses the best way to translate a problem formulation and choice of optimization algorithm into an efficient solver implementation. In applications to the image processing pipeline deconvolution in the presence of Poisson-distributed shot noise, and burst denoising, we show that a few lines of ProxImaL code can generate a highly-efficient solver that achieves state-of-the-art results. We also show applications to the nonlinear and nonconvex problem of phase retrieval.

Past Seminars

...

Locating Features in Detector Images with Machine Learning

Date: Feb. 7, 2pm

Speaker: David Schneider

...

...

Tractable quantum leaps in battery materials and performance via machine learning

Date: Jan. 17, 2017
Speaker: Austin Sendek

...

...

Deep Learning and Computer Vision in High Energy Physics

Date: Dec 6, 2016

Speaker: Michael Kagan

...

https://arxiv.org/abs/1511.05190
https://arxiv.org/abs/1611.01046

...

Label-Free Supervision of Neural Networks with Physics and Domain Knowledge

Date: Oct 18, 2016

Speaker: Russell Stewart

...

...

Can machine learning teach us physics? Using Hidden Markov Models to understand molecular dynamics.

Date: Sept 21, 2016

Speaker: T.J. Lane

...

...

On-the-fly unsupervised discovery of functional materials

Date: Aug 31, 2016

Speaker: Apurva Mehta

...

...

Machine Learning and Optimization to Enhance the FEL Brightness

Date: Aug 17, 2016

Speakers: Anna Leskova, Hananiel Setiawan, Tanner M. Worden, Juhao Wu

...

...

Automated tuning at LCLS using Bayesian optimization

Date: July 6, 2016

Speaker: Mitch McIntire

...

...

Using Deep Learning to Sort Down Data

Date: June 15, 2016
Speaker: David Schneider

...