LinkedIn AI Academy AI-100: 3 Scaling AI at LinkedIn

LinkedIn AI Academy AI-100: 3 Scaling AI at LinkedIn

1h 43mBeginner2023-05-04

Authors

Daniel Hewlett

Daniel Hewlett

Ankan Saha

Ankan Saha

Birjodh Tiwana

Birjodh Tiwana

Ya Xu

Ya Xu

Jenelle Bray

Jenelle Bray

Sakshi Jain

Sakshi Jain

Suman Sundaresh

Suman Sundaresh

Course details

AI is one of the most important but least understood fields in the world. It’s changing the way we think about business, but it’s changing so fast it’s difficult to know where to begin. If you’re looking to learn more about scaling AI, join LinkedIn’s AI and Machine Learning Engineering team in this beginner-friendly course, the third and final installment of the Linked AI Academy AI-100 series.

Discover the basics of how AI works so you can scale it like a pro. Explore use cases with specific examples of AI applications from LinkedIn. Find out how LinkedIn develops and scales AI for nearly a billion product users. Along the way, these instructors discuss the specifics of applications such as search, recommendations, spam classifiers, fake account selector, anomaly detection, systems and productivity, trust and privacy, standardization, and more.

Skills covered

Artificial Intelligence FoundationsArtificial Intelligence (AI)One-Off

Concepts

Introduction

  • The LinkedIn AI Academy - Applying AI at scale
  • Applications of AI at LinkedIn

Data Representation Applications

  • LinkedIn Economic Graph
  • Standardization part 1 - Information extraction and entity resolution
  • Standardization part 2 - GNN applications
  • Content understanding - Topic modeling and representing content as embeddings

Application 1 - Building Professional Communities

  • PYMK and follow recommendations
  • Helping creators
  • Optimizing feeds and notifications to nurture communities
  • Ads for monetizing the feed

Application 2 - Jobs Marketplace

  • Job seeker - recommendations and notifications
  • LinkedIn Learning recommendations
  • Recruiter
  • Jobs marketplace optimization

Industrialization

  • Tech stack - Offline, online, and nearline components
  • Anomaly detection
  • A B testing

Building Trusted AI Products Responsibly

  • Spam classification
  • Fake accounts
  • Bias in AI models - Fairness
  • Explainability

Conclusion

  • Continuing on with learning AI
40,000 Toman