Skip to content

Piekniewski's blog

On limits of deep learning and where to go next with AI.

  • Main site
  • Blog home
  • About

hex1

Posted May 4, 2016 by Filip Piekniewski

If you found an error, highlight it and press Shift + Enter or click here to inform us.

Comments

comments

Post navigation

hex1

Basic info

I’m proposing a new machine learning meta-architecture for learning forward models. The architecture is called Predictive Vision Model (PVM). In this blog I present my thoughts on how PVM relates to deep learning and the global AI landscape. Occasionally I’ll blog about my sysadmin projects and sci-fi.

See a short bio note here.

Follow

Follow @filippie509

Recent Posts

  • AI - the no bullshit approach
  • DeflAition
  • Autonomous vehicle safety myths and facts, 2020 update.
  • The musings of a transformer
  • AI update, late 2019 - wizards of Oz
  • Reviewing Rebooting AI
  • Civilization from scratch
  • AI circus, mid 2019 update
  • Deep learning and shallow data
  • A brief story of Silicon Valley's affair with AI
  • Autonomous vehicle safety myths and facts, 2019 update
  • Fooled by data
  • Elon and the collective
  • AI winter - update
  • Deep learning - the "why" question.
  • Mathematical foundations of neuroscience
  • Some fun numbers about the human brain
  • 2017 PVM talk at UC Merced
  • Autopsy of a deep learning paper
  • Rebooting AI - postulates
  • AI winter - Addendum
  • AI winter is well on its way
  • Are black holes really so black?
  • Some new ideas for AI benchmarks
  • Autonomous vehicle safety myths and facts, 2018 update
  • Electric shock
  • Mt. intelligence
  • Optimality, technology and fragility.
  • When the tail is bigger than the dog
  • The paradox of reproducibility in statistical research
  • Problems with measuring performance in Machine Learning
  • Silent immobility
  • Autonomous car safety myths and facts
  • Intelligence confuses the intelligent
  • Inside of a nebula
  • The complexity of simplicity - balancing on the Occam's razor
  • Who will figure out intelligence?
  • The meta-parameter slot machine
  • Give me a dataset to train, and I shall move the world
  • Self made time capsule, part 2.
  • Self made time capsule, part 1
  • PVM on the GPU (dev update)
  • What would an autonomous car do?
  • Outside the box
  • Can a deep net see a cat?
  • Scaling up AI
  • Recurrent dreams and filling in
  • Learning physics is the way to go
  • More thoughts on the self driving car
  • Yann LeCun lecture at CMU, 11.2016, a few comments
  • Myths and facts about AI
  • AI and the ludic fallacy
  • Predictive Vision in a nutshell
  • Reactive vs Predictive AI
  • Statistics and dynamics

Archives

  • June 2020
  • April 2020
  • March 2020
  • November 2019
  • October 2019
  • July 2019
  • May 2019
  • April 2019
  • March 2019
  • February 2019
  • January 2019
  • December 2018
  • October 2018
  • September 2018
  • August 2018
  • July 2018
  • June 2018
  • May 2018
  • April 2018
  • February 2018
  • December 2017
  • November 2017
  • October 2017
  • September 2017
  • July 2017
  • May 2017
  • April 2017
  • March 2017
  • February 2017
  • January 2017
  • December 2016
  • November 2016
  • October 2016
  • August 2016
  • July 2016
  • May 2016
  • April 2016

Categories

  • General
  • Machine learning
  • Scifi
  • Sysadmin

Meta

  • Log in
  • Entries feed
  • Comments feed
  • WordPress.org
Proudly powered by WordPress | Theme: sosimple by Fernando Villamor Jr..

Thank you very much for your help. We will fix it soon!

We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.Ok