Started\
0:00 Udemy 101 Getting the Most From Th
2:10 [Activity] Install Anaconda, cours
11:16 Course Roadmap
15:09 What Is a Recommender System
17:57 Types of Recommenders
21:19 Understanding You through Implici
25:45 Top-N Recommender Architecture
31:38 [Quiz] Review the basics of recom
to Python [Optional]\
36:25 [Activity] The Basics of Python
41:29 Data Structures in Python
46:46 Functions in Python
49:32 [Exercise] Booleans, loops, and a
Recommender Systems\
53:24 TrainTest and Cross Validation
57:14 Accuracy Metrics (RMSE, MAE)
1:01:20 Top-N Hit Rate - Many Ways
1:05:55 Coverage, Diversity, and Novelt
1:10:51 Churn, Responsiveness, and AB T
1:15:58 [Quiz] Review ways to measure y
1:18:54 [Activity] Walkthrough of Recom
1:25:47 [Activity] Walkthrough of TestM
1:30:56 [Activity] Measure the Performa
4.A Recommender Engine Framework\
1:33:21 Our Recommender Engine Architec
1:40:48 [Activity] Recommender Engine W
1:48:35 [Activity] Review the Results o
Filtering\
1:51:46 Content-Based Recommendations,
2:00:45 K-Nearest-Neighbors and Content
2:04:44 [Activity] Producing and Evalua
2:10:08 A Note on Using Implicit Rating
2:13:45 [Activity] Bleeding Edge Alert!
2:18:16 [Exercise] Dive Deeper into Con
Collaborative Filt
2:22:42 Measuring Similarity, and Spars
2:27:32 Similarity Metrics
2:36:04 User-based Collaborative Filter
2:43:29 [Activity] User-based Collabora
2:48:28 Item-based Collaborative Filter
2:52:43 [Activity] Item-based Collabora
2:55:07 [Exercise] Tuning Collaborative
2:58:38 [Activity] Evaluating Collabora
3:00:07 [Exercise] Measure the Hit Rate
3:02:25 KNN Recommenders
3:06:29 [Activity] Running User and Ite
3:08:55 [Exercise] Experiment with diff
3:13:20 Bleeding Edge Alert! Translatio
Factorization Methods\
3:15:50 Principal Component Analysis (P
3:22:22 Singular Value Decomposition
3:29:18 [Activity] Running SVD and SVD
3:33:05 Improving on SVD
3:37:39 [Exercise] Tune the hyperparame
3:39:37 Bleeding Edge Alert! Sparse Lin
to Deep Learning [Option
3:43:08 Deep Learning Introduction
3:44:38 Deep Learning Pre-Requisites
3:52:52 History of Artificial Neural Ne
4:03:43 [Activity] Playing with Tensorf
4:15:45 Training Neural Networks
4:21:33 Tuning Neural Networks
4:25:25 Activation Functions More Depth
4:36:01 Introduction to Tensorflow
4:47:31 [Activity] Handwriting Recognit
5:12:54 Introduction to Keras
5:15:42 [Activity] Handwriting Recognit
5:25:35 Classifier Patterns with Keras
5:29:34 [Exercise] Predict Political Pa
5:39:29 Intro to Convolutional Neural N
5:48:28 CNN Architectures
5:51:23 [Activity] Handwriting Recognit
6:00:01 Intro to Recurrent Neural Netwo
6:07:39 Training Recurrent Neural Netwo
6:11:01 [Activity] Sentiment Analysis o
6:22:03 Tuning Neural Networks
6:26:42 Neural Network Regularization T
Learning for Recommender Systems
6:33:03 Intro to Deep Learning for Reco
6:35:22 Restricted Boltzmann Machines (
6:43:25 [Activity] Recommendations with
6:56:12 [Activity] Recommendations with
7:03:23 [Activity] Evaluating the RBM R
7:07:07 [Exercise] Tuning Restricted Bo
7:08:50 Exercise Results Tuning a RBM R
7:10:06 Auto-Encoders for Recommendatio
7:14:33 [Activity] Recommendations with
7:21:56 Clickstream Recommendations wit
7:29:20 [Exercise] Get GRU4Rec Working
7:32:02 Exercise Results GRU4Rec in Act
7:39:54 Bleeding Edge Alert! Deep Facto
7:45:43 More Emerging Tech to Watch
it Up\
7:50:58 [Activity] Introduction and Installation of Apache Spark
7:56:48 Apache Spark Architecture
8:02:01 [Activity] Movie Recommendations with Spark, Matrix Factorization, and ALS
8:08:04 [Activity] Recommendations from 20 million ratings with Spark
8:13:01 Amazon DSSTNE
8:17:43 DSSTNE in Action
8:27:08 Scaling Up DSSTNE
8:29:23 AWS SageMaker and Factorization Machines
8:33:48 SageMaker in Action Factorization Machines on one million ratings, in the cloud
8:41:27 Other Systems of Note (Amazon Personalize, RichRelevance, Recombee, and more)
8:51:57 Recommender System Architecture
Challenges of Recommender Systems\
9:02:11 The Cold Start Problem (and solutions)
9:08:23 [Exercise] Implement Random Exploration
9:09:18 Exercise Solution Random Exploration
9:11:36 Stoplists
9:16:24 [Exercise] Implement a Stoplist
9:16:57 Exercise Solution Implement a Stoplist
9:19:20 Filter Bubbles, Trust, and Outliers
9:24:59 [Exercise] Identify and Eliminate Outlier Users
9:25:44 Exercise Solution Outlier Removal
9:29:44 Fraud, The Perils of Clickstream, and International Concerns
9:34:18 Temporal Effects, and Value-Aware Recommendations
Studies\
9:37:49 Case Study YouTube, Part 1-2
9:48:36 Case Study Netflix, Part 1-2
Approaches\
9:56:31 Hybrid Recommenders and Exercise
9:59:25 Exercise Solution Hybrid Recommenders
Up\
10:03:43 More to Explore