What is cross-validation and what is it used for?
Machine Learning / AI
What metrics are used for segmentation and object detection?
What are stride and padding? How do they affect the output size of a convolution?
How to perform cross-validation on time series?
What is Bayes' theorem?
What are parametric and non-parametric criteria, and when are they used?
What is beat tracking?
How is KV-cache implemented in autoregressive transformer inference?
What is sampled softmax and what is its advantage in terms of compute?
What mechanisms of encapsulation are implemented in Python?
What is CV-leak and what are its sources?
How many weights are trained in a convolutional layer with a 5x5 kernel and 10 filters?
What is the Unigram language model in tokenization (like in SentencePiece)?
What is the difference between multithreading and multiprocessing, and when is it better to use each?
What happens if you remove a tree from boosting?