The ML Basics and Concepts Series
A guided series on the core ideas that shape how machine learning models learn, generalize, and fail.
Posts in this topic
-
Train, Validation, and Test Sets: Measuring Generalization Correctly
How to split data, prevent leakage, choose models, and obtain an honest estimate of performance on unseen examples.
-
Bias and Variance: Understanding Underfitting and Overfitting
How bias, variance, and Bayes error explain a model's generalization error—and what training and validation results can tell us.
The AI Frontiers Series: From Models That Answer to Systems That Act
A roadmap for exploring agentic AI, reasoning, memory, tool use, multimodal systems, efficient models, evaluation, and safety.
Posts in this topic
-
What Makes an AI System Agentic?
A practical guide to the difference between models, workflows, and agents—and to the feedback loop, tools, state, and safeguards that make agency possible.
Reflections
Posts in this topic
-
Why Blog? Why Now?
Writing as a way to filter the noise, keep knowledge alive, and sharpen the mind in an age of abundant information and generative AI.