How to use BERT in a SQuAD-style QA task?
Machine Learning / AI
What are the modern TTS models (Tortoise, XTTS, StyleTTS2, ElevenLabs)?
What is CUDA and what are its main concepts (kernel, grid, block, thread)?
Are there any organizational or technical questions?
What is the purpose of pruning a decision tree?
What feature selection methods exist?
What is padding mask and why must it be considered in attention?
What is test-time augmentation (TTA)?
What is cross-validation and what is it used for?
What is the difference between linear and logistic regression?
What is the ROC AUC metric?
What is ELBO and why is it maximized?
What is an ROC curve?
What are the bottlenecks when deploying GNN in production?
What is HyDE (Hypothetical Document Embeddings)?
What regularization methods of neural networks do you know?
What is a probabilistic retrieval model?
What is label smoothing in image classification?
What is TD3 and what three improvements does it make to DDPG?
What criteria of informativeness are used when constructing a decision tree?