How Lucky is a Bowl of Lucky Charms?

A team of students helped design and carry out an experiment to determine whether bowls of Lucky Charms are equally “lucky” over the course of a box of cereal. Turns out, not so much…

Unveiling the Magic Behind Stable Diffusion 3

Stable Diffusion 3 is the new state-of-the-art for image synthesis. Also, its innovative approaches explain its astonishing results, setting a new standard.

How to Optimize Recommendation Results with Genetic Algorithm

Recommender systems have been applied in various industries nowadays, including e-commerce, marketing, video streaming, financial industries and so on. There are different types of algorithms out…

Probably the Best Data Visualisation for Showing Many-to-Many Proportion In Python

Python data visualisation library PyCirclize to draw Chord Charts Diagrams with links to show proportion, correlation, for data science and analysts

Demystifying Mixtral of Experts

Mixtral 8x7B, Mistral AI’s new sparse Mixtures of Experts LLM, recently made a lot of waves, with dramatic headlines such as “Mistral AI Introduces Mixtral 8x7B: a Sparse Mixture of Experts (SMoE)…

Top Important Computer Vision Papers for the Week from 04/03 to 10/03

Every week, several top-tier academic conferences and journals showcased innovative research in computer vision, presenting exciting breakthroughs in various subfields such as image recognition…

When Do You Self Join? A Handy Trick

Often Data Analysts ad Data Engineers need to find patterns in data that are not obvious. Howevre the insights can be generated and patterns identified by using common SQL practices, like Self Join…

Fine-tune Mixtral-8x7B Quantized with AQLM (2-bit) on Your GPU

Mixtral-8x7B is one of the best open LLMs. It is also very challenging to fine-tune it on consumer hardware. The model occupies 96.8 GB of memory when fully loaded. Fine-tuning would require even…

Machine Learning in a non-Euclidean Space

This post was co-authored with Aniss Medbouhi and is based on his research under Prof. Danica Kragic’s supervision, at the KTH lab in the Robotics Perception and Learning Division. M: Hi Aniss…

The Mathematics and Foundations behind Spectral Clustering

Spectral clustering is a graph-theoretic clustering technique that utilizes the connectivity of data points to perform clustering and is a technique of unsupervised learning. Data points that lie…