Share Description
In this course, you will :
- This course will help you develop that skill while also going over some of the most commonly asked interview questions at large tech companies.
- Work through these problems step by step, focusing on how to design machine learning systems rather than just answering trivia-style questions.
Syllabus :
1. Practical ML Techniques/Concepts
- Performance and Capacity Considerations
- Training Data Collection Strategies
- Online Experimentation
- Embeddings
- Transfer Learning
- Model Debugging and Testing
2. Search Ranking
- Problem Statement
- Metrics
- Architectural Components
- Document Selection
- Feature Engineering
- Training Data Generation
- Ranking
- Filtering Results
3. Feed Based System
- Problem Statement
- Metrics
- Architectural Components
- Tweet Selection
- Feature Engineering
- Training Data Generation
- Ranking
- Diversity
- Online Experimentation
4. Recommendation System
- Problem Statement
- Metrics
- Architectural Components
- Feature Engineering
- Candidate Generation
- Training Data Generation
- Ranking
5. Self-Driving Car: Image Segmentation
- Problem Statement
- Metrics
- Architectural Components
- Training Data Generation
- Modeling
6. Entity Linking System
- Problem Statement
- Metrics
- Architectural Components
- Training Data Generation
- Modeling
7. Ad Prediction System
- Problem Statement
- Metrics
- Architectural Components
- Feature Engineering
- Training Data Generation
- Ad Selection
- Ad Prediction
