What are the features of active learning in computer vision?
Machine Learning / AI
What are the features of online recommendation evaluation (CTR, conversion)?
How can a customer understand that a feature is insignificant without using feature importance in a black box model?
What is neighborhood aggregation and what functions are used (mean, sum, max, LSTM)?
How does dropout help prevent overfitting in neural networks?
Which is faster, searching in a dictionary or in a list, and why?
What regularization methods exist for nonlinear models?
Can it be guaranteed that linear regression predicts values within a given range for any input data?
What regularization methods are applicable to neural networks?
What is diversity and MMR (Maximal Marginal Relevance)?
What are the production issues of OCR (low resolution, skew, shadows)?
What is the difference between linear regression and other methods when working with categorical features?
What is query log mining and what signals does it extract?
What is the asymptotic complexity O and Omega?
What is A/B testing for ML models and what business metrics are important?
What are Tensor Cores and what operations do they accelerate?
Is it necessary to scale features for linear regression and other models?
How do ELMo embeddings differ from BERT?
What is SentencePiece and why is it needed for languages without explicit delimiters?
What is the difference between prompting instructive models and basic LM?