Generative model that won the 2024 Physics Nobel Prize - Restricted Boltzmann Machines (RBM)

CORRECTION: The score for BE is 6 and for BD is -1.

Restricted Boltzmann Machines (RBMs) are a type of neural network based on Hopfield models, created by Geoff Hinton, winner of the 2024 Physics Nobel Prize.
In this video you'll find a gentle introduction to RBMs and their training process, using a real-life example with people and pets.

40% discount promo code: serranoyt

Introduction: (0:00)
Mystery: (0:17)
Scores: (4:39)
Probabilities: (7:30)
Training (11:09)
Contrastive Divergence: (13:37)
Small Problem: (15:33)
Gibbs Sampling: (16:33)
Updating Weights: (20:56)
Sampling Problems: (22:58)
Independent Sampling: (24:27)
Picking Random Samples with Conditions: (28:30)
Picking Completely Random Samples: (31:05)
Summary: (35:03)
Conclusion: (35:57)

[chaitralisamant]

this is the only ML tutorial i’ve seen that makes everything so clear. cannot emphasize the importance of this as a beginner, thank you so much!!

[AdityaSingh-kptj]

Learning with examples first is always better than starting with math, Now when I read the math behind RBM it makes more sense since I have something to relate too!
Thank you for this wonderful presentation :)

[jao]

Please never stop making these videos!

[souravverma]

This is the best tutorial that I came across from introduction to RBM. Looking forward to more such AI tutorials from you.

[blesucation]

Just want to leave a comment so that more people could learn from your amazing videos! Many thanks for the wonderful and fun creation!!!

[jonashetterich]

Chapeau to how much effort you put into this tutorial. ML-Grads like me are dependent on such videos. Love from Germany!

[danfiel]

Great Work! You're video is the first one I've watched to properly explain RBM to people who dont really know much about math.

[hotlunch]

This video is a game-changer, I had no idea how RBM's worked before. Thanks!

[grantwiersum]

Whoa....I was warned these were super hard to understand but that was so well explained. You are amazing

[ribbydibby]

This clip clarified a lot about RBMs for me. Perfect combination of simple examples and the math behind it which makes it easy to understand. I don't get why literature on this or similar topics aimed to teach has to only focus on the math part/formulas which is much more time consuming to understand and in the end doesn't provide as good intuition as your approach of teaching a subject. Thanks for the video!

[ajit_edu]

Your tutorials are addictive. So clearly explained, that you think of making use of it in real world !!

[HoustonPL]

I love your videos and methods of teaching relatively difficult stuff in easy way. Keep up the great job!

[AlirezaMomenzadeh-os]

I just have some doubt about some possible scenarios that you explained at the beginning of the video. For example, in your explanations, you explained that the score for the scenario BD is equal to -1. But, then in the table, we see that the score for this scenario is not -1, instead, it is -2. And this inconsistency happens for some other scenarios as well. Thank you very much for your clear explanations.

[PradeepMahato]

Explanation with visual representation, the best tutorial I have ever seen. RBM is very well explained !!

[artmiss-xo]

wow this was one of the best tutorials i've seen about RBM

[kennys]

Nice. Topic I like most (in ai) posted on my birthday. I have been following you for a some months, good content, keep up the good work!

[vijtad]

Explained very well with practical example. Now I understand how Gibbs sampling is used in RBM. Thank you very much.

[English-bhng]

The most easy and understandable video about RBM. Thanks.

[zcjsword]

I read RBM's wikipedia page twice but was still confused. The video clarifies everything. Thanks!

[andrewlane]

you explain concepts so eloquently -- thank you for these explanations