Skip to content
calculated | content

calculated | content

  • About
  • Contact
  • Home

Thoughts on Data Science, Machine Learning, and AI

  • About
  • Contact
  • Home

Month: February 2017

Why Deep Learning Works 3: BackProp minimizes the Free Energy ?

 ?Deep Learning is presented as Energy-Based Learning Indeed, we train a neural network by running BackProp, thereby minimizing the model error–which is … More

Blog at WordPress.com.
  • Follow Following
    • calculated | content
    • Join 735 other followers
    • Already have a WordPress.com account? Log in now.
    • calculated | content
    • Customize
    • Follow Following
    • Sign up
    • Log in
    • Report this content
    • View site in Reader
    • Manage subscriptions
    • Collapse this bar