What is CTC loss in OCR?
Machine Learning / AI
What is Rainbow DQN and what components does it combine?
Why does BERT give better quality on text classification tasks than TF-IDF with logistic regression?
How does INT8 quantization differ from INT4?
What feature selection methods exist?
What is TensorRT-LLM and where does it have advantages?
What are quantized embeddings and how are they used in production search?
What is sequential testing (mSPRT, always valid)?
How are MAP and MRR metrics calculated in ranking tasks?
What is data drift?
What is BLEU and in what tasks is it used? What are the problems with this metric?
What is stream-based active learning?
What metric should be maximized in a credit scoring task to accurately identify people who should be granted a loan?
What approaches are used for anomaly detection in logs and metrics?
What is OSM and how to extract labels from it?
How to catch the moment of data distribution change (data drift)?
What is a privacy budget?
What is weight of evidence (WoE) and information value (IV)?
What is collaborative filtering and what are the basic algorithms (user-based, item-based)?
What is FastText and how does it solve the OOV problem?