From a probability density function to random samples Photo by Moritz Kindler on UnsplashT here are different methods for updating a reinforcement learning agent’s policy at each iteration. A few weeks ago we started experimenting with replacing our current method with a Bayesian inference step. Some of the data workloads within our agent are written…

In 2022, my portfolio helped me get my first DS job. Now I’m tearing it down and starting again from scratch Image by David Pisnoy on UnsplashIf you’re a data scientist or aspiring data scientist, keeping an online portfolio is a fantastic way to showcase your skills to prospective employers. I made my first portfolio…

An illustrated and intuitive guide on how Neural Networks learn Welcome to Part 2 of the Deep Learning Illustrated series. In the previous article (definitely read that first!), we covered how a neural network works and how a trained neural network makes predictions. In this article, we’ll delve into the training process and explore how…

How should we choose between label, one-hot, and target encoding? 15 min read · 16 hours ago Why Do We Need Encoding? In the realm of machine learning, most algorithms demand inputs in numeric form, especially in many popular Python frameworks. For instance, in scikit-learn, linear regression, and neural networks require numerical…

Implementing a simple neural network framework from scratch Trees — the core of computation. Source: Adrian Infernus on Unsplash.Despite doing some work and research in the AI ecosystem for some time, I didn’t truly stop to think about backpropagation and gradient updates within neural networks until recently. This article seeks to rectify that and will…

Go from nothing to a complete dataframe with Python Photo by Joshua Sortino on Unsplash.After submitting a recent article to Towards Data Science’s editorial team, I received a message back with a simple inquiry: are the datasets licensed for commercial use? It was a great question — the datasets in my draft came from Seaborn,…

Practical lessons from upgrading Bed-Reader, a bioinformatics library Rust and Python reading DNA data directly from the cloud — Source: https://openai.com/dall-e-2/. All other figures from the author.Would you like your Rust program to seamlessly access data from files in the cloud? When I refer to “files in the cloud,” I mean data housed on web…

This blog post shows how to easily run an LLM locally and how to set up a ChatGPT-like GUI in 4 easy steps. Photo by Liudmila Shuvalova on UnsplashThanks to the global open source community, it is now easier than ever to run performant large language models (LLM) on consumer laptops or CPU-based servers and…

How Neural Networks are strong tools for solving differential equations without the use of training data Photo by Linus Mimietz on UnsplashDifferential equations are one of the protagonists in physical sciences, with vast applications in engineering, biology, economy, and even social sciences. Roughly speaking, they tell us how a quantity varies in time (or some…

A step-by-step illustration of how to use SOLID to solve a refactoring challenge Photo by Lucas Davies on UnsplashIntroduction Code refactor challenges are well-known by software engineers, but less so by data scientists, though data scientists can also highly benefit from practising such challenges. By practising these, especially when applying the SOLID principles, you learn…