Unfolding the universe of possibilities..

Navigating the waves of the web ocean

Generating Images with Stable Diffusion and OnnxStream on the Raspberry Pi

Learn how to use OnnxStream to generate images with Stable Diffusion XL Turbo on the Raspberry Pi! Images generated using SDXL Turbo on the Raspberry Pi, each taking ~3 minutes | Source: Author In my last article, I shared how to

Evaluating Text Generation in Large Language Models

Metrics to measure the gap between neural text and human text Continue reading on Towards Data Science »

Building Blocks of Time: The Mathematical Foundation and Python Implementation of RNNs

Is being able to build and train machine learning models from popular libraries sufficient for machine learning users? Probably not for too long. With tools like AutoAI on the rise, it is likely that a lot of the very traditional

To Data or Not to Data.

The question is not anymore whether we can solve the problem with AI but to what extent it returns sustainable and reliable results. Good… Continue reading on Towards Data Science »

A Guide to Data Engineering Infrastructure

Automate resource provisioning with modern tools Continue reading on Towards Data Science »

Deploying LLMs locally with Apple’s MLX framework

A technical deep dive into the new deep learning library MLX Continue reading on Towards Data Science »

A Weekend AI Project: Running Speech Recognition and a LLaMA-2 GPT on a Raspberry Pi

A fully offline use of Whisper ASR and LLaMA-2 GPT Model Continue reading on Towards Data Science »

Evaluating Cinematic Dialogue — Which syntactic and semantic features are predictive of genre?

This article explores the relationship between a movie’s dialogue and its genre, leveraging domain-driven data analysis and informed… Continue reading on Towards Data Science »

TE2Rules: Explaining “Why did my model say that?”

Taking model explainability beyond images and text In the rapidly evolving landscape of artificial intelligence, recent advancements have propelled the field to astonishing heights, enabling models to mimic human-like capabilities in handling both images and text. From crafting images with an

Pooling Layers For Convolutional Neural Networks (CNN)

What are pooling layers and their different types Continue reading on Towards Data Science »