Predicting Movie Recommendations by Leveraging Deep Learning and MovieLens Data (Part 3)

BST Results Summary (10M)
Tuned hyperparameters for BST 5
Train and Validation Epoch vs Loss Graph for BST 5
Test RMSE for BST 5
Tuned hyperparameters for BST 6
Train and Validation Epoch vs Loss Graph for BST 6
Test RMSE for BST 6
dataPreprocessor function in Autoencoder model
MMSE calculation
This image is sourced from Sedhain and describes the structure of AutoRec
This image is sourced from González-Fierro and describes the structure of DeepAutoRec (Deep AE )
Autorec parameters tried
AutoRec with Leaky ReLU
Deep AE parameters attempted
Adding Gaussian noise to input
Best Autoencoder: Deep AutoRec Model Structure
Train and Validation Epoch vs RMSE Graph for Deep AutoRec
Train and Validation Epoch vs Loss Graph for Deep AutoRec
Weights of Deep AutoRec
Movie Ratings Prediction of User with ID = 2000 for Deep AutoRec
Percentage of Ratings Correct of User with ID = 2000 for Deep AutoRec
Recommended Movies for User with ID = 2000 based on Predicted Ratings for Deep AutoRec
Word2Vec Content Based Filtering Concept (from Grimaldi 2018)
Word2Vec Model Architecture (from Karani, 2018)
Training set word2vec embeddings and specific parameters
Visualize word2vec embeddings by reducing dimensions using UMAP
Visualize word2vec embeddings by reducing dimensions using t-SNE
Get recommendations outputs

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store