Learn what you need to know to master recommender systems with our TL;DR course.

Who are the instructors?

The instructors are recsyslabs Co-Founders Dr. Ernesto Diaz-Aviles & Dr. Igor Brigadir

We have been designing and building recommender systems in production for the past 15 years and it is time we share our knowledge with the community. We have put together a course to teach you the TL;DR knowledge you need to get you started to understand, design, and build recommender systems yourself. – Ernesto & Igor

When does it start and how long does it take to complete?

• We will offer the course on a rolling basis every week, so you can start at any time. Next week's batch starts on October 19, 2021 at TK: TIME? EVENING PST?
• The 7 modules of the course will be completed in 4 sessions of 2 hours each.
• The course also includes 4 office-hours sessions of 30 minutes each in small groups of up to 10 people.

How much does it cost?

• The cost is $1250.00, which includes all course modules and 4 office-hours sessions.
• We offer scholarships of up to 50% discount for women in science, LatinX, and other underrepresented minorities in Machine Learning. Please fill in this form to apply: TK: FORM.

Register now to secure your place

Are you ready? Then let's do it! Here is the registration form: TK: LINK TO REG FORM . We hope to see you soon!

What is the format of the course?

• This course is instructor-led and it will be delivered live (online), so you can join us wherever you are. This course is not pre-recorded. The course will be delivered in English.
• We will use Python for the implemenentations and we will use Jupyter Notebooks to facilitate the exchange of ideas and discussion.
• We offer the option of office hours in small groups so you can get the best of the course.

What you will learn from this course – Syllabus

1.0 Intro to Recommender Systems as an application of Machine Learning (ML)

• Non-Personalized
• Content-based
• Nearest Neighbor Collaborative Filtering

2.0 Collaborative Filtering (CF) deep dive

• CF in more detail
• Explicit feedback
• Implicit feedback

3.0 Recommender Systems Evaluation Metrics

• How do you measure recommender system’s performance?
• Recommender Systems Tasks
• Offline vs Online Evaluation

4.0 Matrix Factorization (MF) for CF and advanced techniques

• Learning embeddings / latent factors to represent user and items
• Main algorithms used for MF
• MF at scale

5.0 Deep Learning for Recommender Systems

• Automatic feature extraction for text and image items using deep learning
• Content-based (CB) recommendations revisited
• Hybrid recommender systems: CB + CF

6.0 Recommender Systems in production at scale

• Canonical Machine Learning (ML) pipeline for recommender systems in production
• MLOps applied to recommender systems
• Example of a scalable architecture

7.0 Recommender Systems products

• Product manager perspective for recommender systems based on Machine Learning
• What users want?
• Considerations designing respectful and privacy-by-default recommender systems

∎