In this course, you apply your knowledge of classification models and embeddings to build a ML pipeline that functions as a recommendation engine. This is the fifth and final course of the Advanced Machine Learning on Google Cloud series.
Overview
Syllabus
- Welcome to Recommendation Systems on Google Cloud
- Welcome to Recommendation Systems on Google Cloud
- Recommendation Systems Overview
- Introduction
- Types of Recommendation Systems
- Content-Based or Collaborative
- Recommendation System Pitfalls
- Discussion
- Reading: Recommendation Systems Overview
- Recommendation Systems Overview
- Content-Based Recommendation Systems
- Content-Based Recommendation Systems
- Similarity Measures
- Building a User Vector
- Making Recommendations Using a User Vector
- Making Recommendations for Many Users
- Lab intro: Create a Content-Based Recommendation System
- Implementing a Content-Based Filtering using Low Level TensorFlow Operations
- Using Neural Networks for Content-Based Recommendation Systems
- Lab Intro: Create a Content-Based Recommendation System Using a Neural Network
- Using Neural Networks for Content-Based Filtering
- Summary
- Readings: Content-Based Recommendation Systems
- Content-Based Recommendation Systems Quiz
- Collaborative Filtering Recommendations Systems
- Types of User Feedback Data
- Embedding Users and Items
- Factorization Approaches
- The ALS Algorithm
- Preparing Input Data for ALS
- Creating Sparse Tensors For Efficient WALS Input
- Instantiating a WALS Estimator: From Input to Estimator
- Instantiating a WAL Estimator: Decoding TFRecords
- Instantiating a WALS Estimator: Recovering Keys
- Instantiating a WALS Estimator: Training and Prediction
- Lab Intro: Collaborative Filtering with Google Analytics Data
- Collaborative Filtering on Google Analytics data
- Issues with Collaborative Filtering
- Cold Starts
- Readings: Collaborative Filtering Recommendations Systems
- Collaborative Filtering Recommendations Systems
- Neural Networks for Recommendation Systems
- Hybrid Recommendation Systems
- Lab Intro: Designing a Hybrid Recommendation System
- Lab Intro: Designing a Hybrid Collaborative Filtering Recommendation System
- Lab Intro: Designing a Hybrid Knowledge-based Recommendation System
- Lab Intro: Building a Neural Network Hybrid Recommendation System
- ML on GCP: Hybrid Recommendations with the MovieLens Dataset
- Context-Aware Recommendation Systems
- Context-Aware Algorithms
- Contextual Postfiltering
- Modeling Using Context-Aware Algorithms
- YouTube Recommendation System Case Study: Overview
- YouTube Recommendation System Case Study: Candidate Generation
- YouTube Recommendation System Case Study: Ranking
- Summary
- Readings: Neural Networks for Recommendation Systems
- Neural Networks for Recommendations
- Reinforcement Learning
- Introduction to module
- Introduction to Reinforcement Learning
- The reinforcement learning framework and workflow
- Model-based and model-free reinforcement learning
- Value-based reinforcement learning
- Policy-based reinforcement learning
- Contextual bandits
- Applications of reinforcement learning
- Reinforcement Learning
- Readings: Reinforcement Learning
- Lab Intro
- Applying Contextual Bandits for Recommendations with Tensorflow and TF-Agents
- Lab Review
- Summary
- Course Summary
- Specialization Summary
- All Course Readings
- Your Next Steps
- Course Badge
