Machine Learning
Posts about Machine Learning
Marimo vs Jupyter Notebook: Which Python Environment is Best?
I just spent three hours debugging a machine learning pipeline, only to realize I had executed cell 14 before cell 12.
Numpyro: Probabilistic Programming That Doesn’t Waste My Time
I remember the bad old days of probabilistic programming. You’d define a hierarchical model, hit “sample,” and then—I’m not joking—go watch an entire.
TF 2.18 & Keras: Real-World Performance Review
I finally bit the bullet last week. After ignoring the notification icons for two months, I upgraded our main training pipeline to TensorFlow 2.18.
RNNs Aren’t Dead: Liquid Networks in Keras 3
I distinctly remember the funeral we all held for Recurrent Neural Networks around 2019. The Transformer architecture had just walked into the room, eaten.
Keras in Late 2025: Why Transfer Learning Is Finally Boring
I spent yesterday afternoon trying to squeeze a Vision Transformer (ViT) onto a consumer-grade GPU. A few years ago, this would have been a three-coffee.
Mastering Modern Keras: Multi-Backend Workflows and Ecosystem Integration
Introduction: The Evolution of Deep Learning Frameworks The landscape of deep learning has undergone a seismic shift in recent years.
Mastering Local LLM Development: From Synthetic Data to Scalable Pipelines
The landscape of Artificial Intelligence is undergoing a seismic shift. While massive proprietary models hosted in the cloud dominated the early.
Unlocking Bacterial Metabolism: Deep Learning and Knowledge Graphs with the IBIS Framework
The landscape of bacterial genomics is undergoing a seismic shift. As sequencing technologies become cheaper and more accessible, the volume of genomic.
Python Quantum Computing: Architecting the Future with Qiskit and Modern Tooling
The intersection of quantum mechanics and software engineering has birthed a new paradigm: Python quantum computing. While the hardware reli…
Marimo Notebooks: The Reactive Revolution in Python Data Science
For over a decade, the Jupyter notebook has been the de facto standard for data exploration, scientific computing, and machine learning education.