Machine Learning / AI
What is test coverage and how to ensure it?
If we want to process multiple files in parallel, what is better to use?
What is SASRec and what is its architecture?
What do the parameters M, ef_construct, ef_search mean in HNSW?
What is spatial pyramid pooling?
Suppose we have a set of tools (applications may differ in fields and names). How is it best to implement or embed this in the context?
How can we incorporate request creation (e.g., leave) into the current RAG pipeline?
What is batch normalization?
Why is Layer Norm used specifically in transformers (and not Batch Norm)?
Tell me about Adam and RMSProp.
We have a dictionary where the key is a string and the value is a tuple. Can we change the value for this key? What will happen?
What is linear regression and what are the options for its solution?
Why is normalization (Layer Norm) needed — why stabilize training?
What other metrics should be added for monitoring document updates (to avoid discovering that after an update, only 3 documents remain instead of 10,000)?
Tell about decorators: what are they and how can they be made?
Can we pass a list as an argument to a function and then modify it inside? What will happen to the old list?
What are the compliance requirements for ML with PII (GDPR, Federal Law-152)?
What is Elliptic Envelope and what are the assumptions of the method?