I recently had the pleasure of visiting the Microsoft Headquarters in Redmond, WA, where I reconnected with my old friend Nikola Metulev at the Windows Building on campus. Nikola and I share a dee...

This project was is about training a model on the classic MNIST dataset — a collection of handwritten digits that’s been a staple in the ML community. Let’s take a friendly tour through the code an...

In this post, I’ll walk you through building a simple machine learning pipeline to classify handwritten digits from the MNIST dataset using scikit‐learn. If you’re looking for a beginner-friendly a...

Understanding machine learning often feels like trying to read a secret language hidden in numbers. One way to decode this language is through visualization. A prime example is the MNIST dataset—a ...

In today’s post, I’m excited to share a beginner-friendly guide on how to train a neural network using Keras on the famous MNIST dataset. Whether you’re new to deep learning or just looking for a c...

Feature Scaling in Machine Learning: A Practical Guide When training machine learning models, having features on vastly different scales can slow down learning or even lead to suboptimal performanc...

[J(w,b) = \frac{1}{2m} \sum_{i=1}^m \left(f_{w,b}\bigl(x^{(i)}\bigr) – y^{(i)}\right)^2] The cost function in linear regression is a way to measure how well a model’s predictions match the actual ...

Matplotlib is a cornerstone in the data science toolkit. Whether you’re prototyping in Jupyter or preparing publication‐quality figures, its flexibility makes it indispensable. In this post, we’ll ...

Pandas is a powerful Python library that has become a cornerstone in data science. It offers fast, flexible, and expressive data structures designed to work with structured (tabular, multidimension...

In the world of data science and machine learning, efficiency is key. NumPy is one of the most powerful libraries in Python, providing high-performance multidimensional arrays and a collection of r...