Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutorial | Edureka
2 likes1,626 views
The document discusses Restricted Boltzmann Machines (RBMs), highlighting their role as energy-based neural networks that function as generative models for probability distributions. It contrasts RBMs with autoencoders and covers their structure, training processes like Gibbs sampling and contrastive divergence, and applications such as collaborative filtering. Additionally, it explains the use of latent factors in data prediction with RBM models.
Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutorial | Edureka
- 3. Agenda ❖ History of RBM ❖ Difference between RBM & Autoencoders ❖ Introduction to RBMs ❖ Energy Based Model & Probabilistic Model ❖ Training of RBMs ❖ Example: Collaborative Filtering
- 6. Restricted Boltzmann Machines (RBMs) are neural networks that belong to Energy Based Models. These are parameterized generative models representing a probability distribution. Introduction to RBMs edureka!
- 8. Visible Layer Hidden Layer Layers of RBMs edureka!
- 9. Visible Layer Hidden Layer Layers of RBMs
- 10. activation f((weight w * input x) + bias b ) = output a
- 11. Working of RBMs X – input W – weight a – activation function w Visible Layer Hidden Layer x + b = a x x x + b = a + b = a edureka!
- 13. RBM: Energy Based Model
- 14. RBM: Energy Based Model Visible Layer Hidden Layer
- 16. RBM: Probabilistic Model Partition Function
- 17. RBM: Probabilistic Model Partition Function
- 19. RBM: Probabilistic Model MNIST’s handwritten numerals Headshots found in Labelled Faces edureka!
- 20. RBM Training
- 21. Copyright © 2017, edureka and/or its affiliates. All rights reserved. 1 2 RBM Training Gibbs Sampling Contrastive Divergence
- 22. Copyright © 2017, edureka and/or its affiliates. All rights reserved. 1 2 RBM Training Gibbs Sampling Contrastive Divergence
- 23. Copyright © 2017, edureka and/or its affiliates. All rights reserved. 1 2 RBM Training Gibbs Sampling Contrastive Divergence
- 24. Copyright © 2017, edureka and/or its affiliates. All rights reserved. 1 2 RBM Training Gibbs Sampling Contrastive Divergence
- 25. RBM: Training to Prediction Step 1 Step 3 Step 4Train the network on the data of all users During inference time take the training data of a specific user Use this data to obtain the activations of hidden neurons Use the hidden neuron values to get the activations of input neurons The new values of input neurons show the rating the user would give Step 2 Step 5 edureka!
- 26. RBM: Example
- 27. Copyright © 2017, edureka and/or its affiliates. All rights reserved. 1 2 RBM: Collaborative Filtering Recognizing Latent Factors in The Data Using Latent Factors for Prediction 0 P = 0.838 0 P = 0.354 1 P = 0.838 1 0 0 1 0 -1 Drama Fantasy Science Fiction Hidden nodes Visible nodes Lord of the Rings The Matrix Fight Club Harry Potter Titanic The Hobbit
- 28. Copyright © 2017, edureka and/or its affiliates. All rights reserved. 1 2 Recognizing Latent Factors in The Data Using Latent Factors for Prediction 00 1 1 P=0.985 0 P=0.171 0 P=0.290 1 P=0.857 0 P=0.214 -1 P=0.910 Drama Fantasy Science Fiction Hidden nodes Visible nodes Lord of the Rings The Matrix Fight Club Harry Potter Titanic The Hobbit RBM: Collaborative Filtering