Why does L1 regularization zero out some weights, but L2 does not?
Machine Learning / AI
What is MRR and where is it used?
What types of JOINs exist in SQL and how do left join, right join, and inner join differ?
What is the decomposition of time series into trend and seasonality?
What is PPO and how is it more convenient than TRPO in practice?
What regularization methods of neural networks do you know?
How does differentiable NAS (DARTS) differ from RL-based methods?
What is N-BEATS?
What are knowledge graph embeddings (TransE, RotatE, ComplEx)?
What is parallelism in inference?
Почему деревья сильнее переобучаются по сравнению с линейными моделями?
What is popularity bias and how to fight it?
How to technically implement a data storage and alert system for model monitoring?
What is a gradient from a mathematical point of view?
How to handle missing values in a dataset?
Why is BF16 more convenient than FP16 when training large models?
How many people were in the project team?
How was BERT trained? What are MLM and NSP?