What metrics and methods are used to evaluate models and AB testing?
Machine Learning / AI
What is the difference between token classification and sequence classification?
What is GraphSAGE and why is neighbor sampling needed?
What is collaborative filtering and what are the basic algorithms (user-based, item-based)?
What is a safety classifier at the end of a dialogue?
What hyperparameters of HNSW are important (M, efConstruction, efSearch)?
What is video object segmentation and mask tracking (XMem, SAM2)?
What are A100, H100, B200, and their key architectural differences?
What is ZeRO-Offload and when is it justified?
What is the difference between key padding mask and attention mask in PyTorch?
What are AutoGPT and BabyAGI? What are their fundamental limitations?
What is IVF index and why are centroids needed?
What are the features of model validation in medical imaging (FDA, regulation)?
What are jailbreak and indirect prompt injection?
What is adversarial training and its trade-offs?
Do you handle analytics independently?
What is a cosine schedule in diffusion?
What is GPT-4V and what are its real applications?
What types of augmentations are specific to detection (mosaic, mixup)?
How does a decision tree work?