Practical hacks to build new meaningful features on your existing data to turn data analysis processes and machine learning modeling more effective.
Word Embeddings in Language Models
Natural language processing (NLP) has long been a fundamental area in computer science. However, its trajectory changed dramatically with the introduction of word embeddings. Before embeddings, NLP relied primarily on rule-based approaches that treated words as discrete tokens. With word embeddings, computers gained the ability to understand language through vector space representations. In this article, […]
A Gentle Introduction to SHAP for Tree-Based Models
Learn how to use SHAP to transform your XGBoost models from black boxes into transparent, explainable systems that reveal exactly how each feature contributes to every prediction.
Using Quantized Models with Ollama for Application Development
A concise how-to for leveraging large language models locally in constrained settings thanks to the benefits of model quantization.
Tokenizers in Language Models
Tokenization is a crucial preprocessing step in natural language processing (NLP) that converts raw text into tokens that can be processed by language models. Modern language models use sophisticated tokenization algorithms to handle the complexity of human language. In this article, we will explore common tokenization algorithms used in modern LLMs, their implementation, and how […]
10 Python Libraries That Speed Up Model Development
Here are some of the best libraries for speeding model development, with an explanation of how they do it.
Selecting the Right Feature Engineering Strategy: A Decision Tree Approach
A guide to selecting the right feature engineering strategies that may give your data a much better shape for further analyses and machine learning modeling.
Using NotebookLM as Your Machine Learning Study Guide
In this article, you’ll learn how to use NotebookLM to support your machine learning journey.
Encoders and Decoders in Transformer Models
Transformer models have revolutionized natural language processing (NLP) with their powerful architecture. While the original transformer paper introduced a full encoder-decoder model, variations of this architecture have emerged to serve different purposes. In this article, we will explore the different types of transformer models and their applications. Let’s get started. Overview This article is divided […]
A Gentle Introduction to Word Embedding and Text Vectorization
From simple word counting to sophisticated neural networks, text vectorization techniques have transformed how computers understand human language by converting words into mathematical representations that capture meaning and context.