• Skip to content
  • Skip to primary sidebar

Dharmendra S. Modha

My Work and Thoughts.

  • Brain-inspired Computing
    • Collaborations
    • Videos
  • Life & Universe
    • Creativity
    • Leadership
    • Interesting People
  • Accomplishments
    • Prizes
    • Papers
    • Positions
    • Presentations
    • Press
    • Profiles
  • About Me

Archives for September 2010

Manfred Warmuth

September 30, 2010 By dmodha

Today, I had the good fortune to spend time with Manfred Warmuth who is a leading scientist in Computational Learning Theory.

Manfred Warmuth

ABSTRACT: Multiplicative updates multiply the parameters by nonnegative factors. These updates are motivated by a Maximum Entropy Principle and they are prevalent in evolutionary processes where the parameters are for example concentrations of species and the factors are survival rates. The simplest such update is Bayes rule and we give an in vitro selection algorithm for RNA strands that implements this rule in the test tube where each RNA strand represents a different model. In one liter of the RNA soup there are approximately 10^20 different strands and therefore this is a rather high-dimensional implementation of Bayes rule.

We investigate multiplicative updates for the purpose of learning online while processing a stream of examples. The “blessing” of these updates is that they learn very fast because the good parameters grow exponentially. However their “curse” is that they learn too fast and wipe out parameters too quickly. We describe a number of methods developed in the realm of online learning that ameliorate the curse of these updates. The methods make the algorithm robust against data that changes over time and prevent the currently good parameters from taking over. We also discuss how the curse is circumvented by nature. Some of nature’s methods parallel the ones developed in Machine Learning, but nature also has some additional tricks.

Filed Under: Brain-inspired Computing, Interesting People

The thermodynamic temperature of a rhythmic spiking network

September 29, 2010 By dmodha

Paul Merolla, Tristan Ursell, John Arthur published today on arXiv.org a beautiful and unconventional paper that applies concepts from statistical mechanics to spiking neurons:

ABSTRACT: Artificial neural networks built from two-state neurons are powerful computational substrates, whose computational ability is well understood by analogy with statistical mechanics. In this work, we introduce similar analogies in the context of spiking neurons in a fixed time window, where excitatory and inhibitory inputs drawn from a Poisson distribution play the role of temperature. For single neurons with a "bandgap" between their inputs and the spike threshold, this temperature allows for stochastic spiking. By imposing a global inhibitory rhythm over the fixed time windows, we connect neurons into a network that exhibits synchronous, clock-like updating akin to neural networks. We implement a single-layer Boltzmann machine without learning to demonstrate our model.

Filed Under: Brain-inspired Computing

The Human Connectome Project

September 28, 2010 By dmodha

The National Institutes of Health awarded grants totaling $40 million over five years to map the human brain’s connections in high resolution. It is "an ambitious effort to map the neural pathways that underlie human brain function". Here is the website with more information.

Filed Under: Brain-inspired Computing

Horst Simon Named Deputy Director for Berkeley Lab

September 17, 2010 By dmodha

Dr. Horst Simon, our collaborator for "The Cat is Out of the Bag", was named as named Deputy Director of Lawrence Berkeley National Laboratory. See the news here. In related news, Horst Simon will also Chair the Gordon Bell Prize Award Committee.  

Filed Under: Brain-inspired Computing

Primary Sidebar

Follow Me

  • Linkedin
  • Twitter

Recent Tweets

  • "The Air Force has embedded a member of its team, for instance, with IBM researchers working on chips for a neuromo… https://t.co/uUMXDtd00m49 days ago
  • RT @cgvprasad: Fitting end to the #IBMTLE NorCal with another eye opening session by @DharmendraModha !! Overall some interesting topics to…51 days ago
  • An open secret of project management is 'closing open loops'. Loops are of 4 types: tasks that you have assigned s… https://t.co/t9npXYPN6l77 days ago
  • AFRL Anticipates Arrival of Neuromorphic Supercomputer https://t.co/uo34hy7Lbz @IBMResearch80 days ago
  • CALL FOR SUBMISSIONS: The Third Misha Mahowald Prize for Neuromorphic Engineering https://t.co/2cVLV1fq3N121 days ago
  • What’s Next With Computing? https://t.co/GUQFX37ffJ122 days ago
  • The head of IBM's San Jose research center is at home in both the kitchen and the lab https://t.co/7pNMeeLbbQ via… https://t.co/tmdAB2rkXS133 days ago
  • Brain-inspired Computing Positions https://t.co/6clTNBogrM @IBMResearch133 days ago
  • Research Summer Internship in Brain Inspired Computing @IBMResearch https://t.co/IrCSD49t1t134 days ago
  • "The US Air Force Research Lab is testing a 64-chip array of our IBM TrueNorth Neurosynaptic System designed for de… https://t.co/Lp5uhr0Qxa134 days ago

Recent Posts

  • Spiking Optical Flow for Event-based Sensors Using IBM’s TrueNorth Neurosynaptic System
  • Video of Keynote (Commencement Speech) at 2017 UCSD School of Engineering Ring Ceremony
  • Brain-inspired Computing Video Gallery
  • IBM demos event-based gesture recognition using a brain-inspired chip at CVPR 2017
  • Keynote Speech at the Ring Ceremony at UCSD’s Jacobs School of Engineering

Archives by Month

  • 2017: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2016: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2015: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2014: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2013: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2012: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2011: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2010: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2009: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2008: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2007: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2006: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

Evolution: Brain-inspired Computing

Copyright © 2018