There are a lot of explanations elsewhere, here I’d like to share some example questions in an interview setting. What is layer normalization in deep learning?

There are a lot of explanations elsewhere, here I’d like to share some example questions in an interview setting. When fine-tuning BERT (Bidirectional Encoder Representations from Transformers) for your use case, what can go wrong? Or what should you pay attention to?

Previously we’ve covered AB testing on multiple metrics and Holm’s method, today let’s continue with the AB testing series. Can you peek early? The short answer is yes. In general, the advice is to let your experiment run its course and only analyze results when your pre-determined sample size is achieved. But there are…

There are a lot of explanations elsewhere, here I’d like to share some example questions in an interview setting. What are generative models? Here are some tips for readers’ reference: Generative model is a class of models for unsupervised learning where given training data our goal is to try and…

When working on a data science project, we often present charts to our stakeholders to support our discoveries or conclusions. One of the pain-points we’ve been hearing a lot about from our business partners is confusion around how to interpret the plots, typically manifested in questions like the following: “What…

The new year opens with lots of discussions of interesting new papers, following the high tide of the ChatGPT. The intro of FlashAttention is among one of the best ones. …