What features are used in speech models (MFCC, mel-spectrogram)?
Machine Learning / AI
What is the DART mode in boosting?
How to delete duplicate data from a table in SQL?
How does grid search differ from random search? When is random faster?
What are the risks of bias amplification?
What is DistilBERT? What are the quality losses and speed gains?
What are the features of serving CV models on edge devices?
What libraries are used for nearest neighbor search?
Tell me about your most interesting project in the field of NLP and LLM, including architecture and solution evaluation.
How do mean/max pooling differ from learnable pooling?
Do you specialize in computer vision or are you willing to work in other domains, such as NLP?
What is continuous batching and how is it better than static batching?
Why does the model during training occupy more memory than during inference?
What are Informer and Autoformer?
What is class imbalance and how to deal with it?
What is the minimum and comfortable income level for you in rubles?
What are the methods of text processing in NLP from simple to modern neural networks?
What are multi-armed bandits and where are they used instead of A/B tests?