Skip to content

Tag: Deep Learning

Why WeightWatcher Works

September 14, 2020 Charles H Martin, PhD

I am frequently asked, why does weightwatcher work ? The weightwatcher tool uses power law fits to model the eigenvalue density of weight matrices of

Continue reading

WeightWatcher: Empirical Quality Metrics for Deep Neural Networks

February 16, 2020 Charles H Martin, PhD

We introduce the weightwatcher (ww) , a python tool for a python tool for computing quality metrics of trained, and pretrained, Deep Neural Netwworks. pip

Continue reading

Heavy Tailed Self Regularization in Deep Neural Nets: 1 year of research

December 17, 2018 Charles H Martin, PhD

My talk at ICSI-the International Computer Science Institute at UC Berkeley. ICSI is a leading independent, nonprofit center for research in computer science. Why Deep

Continue reading

Why Deep Learning Works II: the Renormalization Group

April 1, 2015 Charles H Martin, PhD

Deep Learning is amazing.  But why is Deep Learning so successful?  Is Deep Learning just old-school Neural Networks on modern hardware?  Is it just that

Continue reading

Why does Deep Learning work?

March 25, 2015 Charles H Martin, PhD

Why does Deep Learning work? This is the big question on everyone’s mind these days.  C’mon we all know the answer already: “the long-term behavior

Continue reading

Foundations: The Partition Function.

November 14, 2013 Charles H Martin, PhD

We are going to examine the Partition function that arises in Deep Learning methods like Restricted  Boltzmann Machines. We take the  pedagogic formalism of Statistical

Continue reading

  • Charles H Martin, PhD

Calculation Consulting

We are a boutique machine learning data science consultancy. How can we help? Email me at info@calculationconsulting.com.

or stop by:
http://calculationconsulting.com
YouTube Channel
Quora

Set up a paid call on Clarity.fm

The Community

Blog Stats

  • 610,007 hits
Follow on WordPress.com

Enter your email address to subscribe to this blog and receive notifications of new posts by email.

Join 735 other followers

Top Posts & Pages

  • Spectral Clustering: A quick overview
    Spectral Clustering: A quick overview
  • Normalization in Deep Learning
    Normalization in Deep Learning
  • is your model overtrained ?
    is your model overtrained ?
  • Foundations: The Partition Function.
    Foundations: The Partition Function.
  • Rank Collapse in Deep Learning
    Rank Collapse in Deep Learning

Recent Posts

  • is your model overtrained ?
  • Simpson’s Paradox and Deep Learning Metrics with Weightwatcher
  • Why WeightWatcher Works
  • WeightWatcher: Empirical Quality Metrics for Deep Neural Networks
  • Towards a new Theory of Learning: Statistical Mechanics of Deep Neural Networks

Top Clicks

  • charlesmartin14.files.wor…
  • charlesmartin14.files.wor…
  • scikit-learn.org/stable/m…
  • charlesmartin14.files.wor…
  • dspace.mit.edu/bitstream/…
  • scikit-learn.org/stable/a…
  • scikit-learn.org/stable/m…
  • arxiv.org/pdf/2002.06716.…
  • gravatar.com/sochinkibiz
  • cbio.ensmp.fr/~jvert/svn/…

Archives

  • April 2021
  • November 2020
  • September 2020
  • February 2020
  • December 2019
  • April 2019
  • December 2018
  • November 2018
  • October 2018
  • September 2018
  • June 2018
  • April 2018
  • December 2017
  • September 2017
  • July 2017
  • June 2017
  • February 2017
  • January 2017
  • October 2016
  • September 2016
  • June 2016
  • February 2016
  • December 2015
  • April 2015
  • March 2015
  • January 2015
  • November 2014
  • September 2014
  • August 2014
  • November 2013
  • October 2013
  • August 2013
  • May 2013
  • April 2013
  • December 2012
  • November 2012
  • October 2012
  • September 2012
  • April 2012
  • February 2012

Social

  • View calccon’s profile on Twitter
  • View charlesmartin14’s profile on LinkedIn
  • View charlesmartin’s profile on GitHub
  • View UCaao8GHAVcRtSZdpObC4_Kg’s profile on YouTube

Meta

  • Register
  • Log in
  • Entries feed
  • Comments feed
  • WordPress.com
logo-i
Blog at WordPress.com.
Cancel

 
Loading Comments...
Comment
    ×