What is the scale of data in the database and clickstream?
Machine Learning / AI
Are batch statistics or saved parameters used in batch normalization during inference?
What are data contracts?
What is Feast and what are its components (offline/online store)?
How to estimate the median response time of a service with a large volume of logs that do not fit into memory?
How does IVF-PQ differ from IVF-Flat?
What is the probabilistic interpretation of ROC-AUC?
What is text normalization (NFC, NFKC) and why should it be done before tokenization?
What is the difference between DWH and Data Lake?
What are slowly changing dimensions (SCD) and how do they affect ML features?
What was the infrastructure configuration?
Why is a B-tree index most commonly used and what is its algorithmic complexity?
Что такое Graph Isomorphism Network (GIN)?
Which HTTP method is better to use for retrieving data by phone number: GET or POST?
How to understand whether a model is good or bad? What metrics exist and what do they mean?
How does top-k differ from top-p (nucleus) sampling?
What are the best practices for writing prompts for GPT-4-class models?
How to understand when to stop feature selection?