Kuhnian Normal and Breakthrough Moments (Revised and Updated)

We have used the Ising equation, over the past fifty years, as an inspirational metaphor for developing energy-based neural networks – such as the Little-Hopfield neural network, the Boltzmann machine, the restricted Boltzmann machine (RBM), and on to more recent developments such as deep learning and GANs. The Kuhnian breakthrough moments were when the Little-Hopfied neural network was originally conceived (1974-1982), and when Hinton introduced latent variables into this network to create the Boltzmann machine. The refinement to create the Restricted Boltzmann machine was also a breakthrough moment. Since then, the same fundamental architecture – based on the Ising equation – has been used in all successive energy-based neural networks. We envision the potential for a new equation to come into play. This video is revised and updated from a prior version.

This short course is not available yet - please OPT-IN with Themesis on the About page to get word AS SOON as this course is released:

Opt-In HERE: www.themesis.com/themesis/

Visit Themesis for the associated blogpost (good links!):
https://themesis.com/2023/02/01/kuhni...

Subscribe to the Themesis YouTube channel easily - click this link: https://www.youtube.com/@themesisinc....