Duration
14 hours (usually 2 days including breaks)
Requirements
- Python programming experience
Audience
- Data Scientists
Overview
A recommender system is an information filtering process that predicts the user’s preferences. Python can be used to program deep learning, machine learning, and neural network recommender systems to help users discover new products and content.
This instructor-led, live training (online or onsite) is aimed at data scientists who wish to use Python to build recommender systems.
By the end of this training, participants will be able to:
- Create recommender systems at scale.
- Apply collaborative filtering to build recommender systems.
- Use Apache Spark to compute recommender systems on clusters.
- Build a framework to test recommendation algorithms with Python.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Course Outline
Introduction
What is AI
- Computational Psychology
- Computational Philosophy
Machine Learning
- Computational learning theory
- Computer algorithms for computational experience
Deep Learning
- Artificial neural networks
- Deep learning vs. machine learning
Preparing the Development Environment
- Setting up Python libraries and Apache Spark
Recommendation Systems
- Building a recommender engine frameworks
- Testing and evaluating algorithms
Collabrative Filtering
- Working with user-based and content-based filtering
- Working with neighbor-based filtering
- Using RBMs
Matrix Factorization
- Using and extending PCA
- Running and improving SVD
- Working with Keras and deep learning neural networks
Scaling with Spark
- Using RDDs and dataframes
- Setting up clusters on AWS / EC2
- Scaling Amazon DSSTNE and SageMaker
Summary and Conclusion