What data deduplication techniques are used in a pipeline?
Machine Learning / AI
What calibration methods for probability exist and how do they work?
What is the Brier score in survival analysis?
What is a re-ranker in RAG? What models are used (cross-encoder, bge-reranker)?
What is a language model?
From what date are you ready to start cooperation in case of a positive decision?
What is the difference between coco mAP and Pascal VOC mAP?
What is DTW (Dynamic Time Warping) and where is it used?
What methods of single-class classification exist?
What methods are available to combat overfitting in neural networks?
Why is sigmoid rarely used as an activation function in neural networks?
What are AlphaGo, AlphaGo Zero, and AlphaZero — key differences?
What is multi-agent RL and what are its non-stationarity problems?
How to interpret the value of the coefficient of determination?
What is self-attention?
Tell about your experience and responsibilities at your current job?
What are the features of training LLM on 100+ GPUs (failure rate, checkpointing)?
What is the idea of a random forest and why does it work?
What is FP8 and where is it used in training/inference?
What are end-to-end dialogue models?