Blog

How Self-Attention Builds Contextual Representations in Transformers

Modern NLP changed when models began representing a token according to the context in which it appears. The word "bank" should not receive the same final representation in a sentence about a loan and in a sentence about a river. I...

• deep learning
• large language models
• rag and information retrieval

Read article ->

Feature Engineering for Tabular Data: How to Use Target Encoding Without Leakage

Deep learning made feature extraction feel almost automatic for images, audio, and text. Tabular machine learning did not follow the same path. In structured business data, the strongest model is often not the one with the most im...

• classical machine learning
• data analysis and statistics
• evaluation and experimentation
• production ml

Read article ->