How does PR-AUC differ from ROC-AUC?
Machine Learning / AI
What is feature hashing trick and where is it appropriate to use?
Как должна выглядеть разметка для обучения трансформера распознавать спецтерминологию?
How is a random forest structured and how does it train in a classification task?
What is mean reciprocal rank (MRR) and where is it used in search evaluation?
Tell us about the architecture of ViT (Vision Transformer): how does an image turn into a sequence of tokens?
Why is there a limit on the number of tokens in transformers?
What is probabilistic programming (PyMC, Stan, NumPyro)?
What must an object have to be an iterator in Python?
What is weight tying between embedding and output projection?
What is FSDP and how does it differ from DDP?
Is it possible to use linear regression for sales forecasting with a non-negativity constraint?
Is it possible to use numpy functions for matrix multiplication in Python?
Is it possible to use two-dimensional positional encoding in transformers working with images?
What are the approaches to handwritten text recognition?
What is target network in DQN?
How is KV-cache implemented in autoregressive transformer inference?
What is a decision transformer and how does it translate RL into supervised learning?
What criteria of informativeness are used when constructing a decision tree?