In this first article, we’ll dive into ggml, the fantastic tensor library created by Georgi Gerganov. How does it work? How is the tensor creation process? Can we start with some simple examples? — Table of content Implementing a simple mathematical function 1.1 The definition of a context 1.2 Initialising tensors 1.3 Forward computation and computation graph 1.4 Compilation and run Final remarks on this first part

DeepMind matrix multiplications on NVIDIA V100, Tesla T4, and a look at FBHHRBNRSSSHK — which is not me typing random letters! — In the previous post, we learned the maths behind the Strassen algorithm and wrote a Python code to run-test it against different matrices sizes. Moreover, we’ve learned that the Holy Grail of linear algebra is an optimization algorithm for matrix multiplication. …

An introduction to the matrix multiplication problem, with applications in Python and JAX — DeepMind recently published an interesting paper that employed Deep Reinforcement Learning to find new Matrix Multiplication algorithms[1]. One of the objectives of this paper is to lower matrix multiplication computational complexity. …

In this tutorial, we’ll build an NLP app starting from DagsHub-MLflow, then diving into deployment in SageMaker and EC2 with the front end in Streamlit. — Table of Contents — 1. Setup DagsHub repo and requirements — — Create your DagsHub repo — — Setup the virtual environment — — Download the data with DVC — 2a. Launch your very first experiment in MLflow — — Naive Bayes model as a backbone for sentiment Classification — — Set up…

Can we use PyTorch in Rust? What are Rust bindings? What’s tch-rs? A look on neural networks in Rust — It’s been a while since the last time when we had a look at Rust and its application to Machine Learning — please, scroll down to the bottom for the previous tutorials on ML and Rust. Today I would like to present you a step forward, introducing neural networks in…

The second part of our NLP exploration: Topic modelling, word embeddings and text similarity through TF-IDF and transfomers — Welcome back to this introduction to the NLP world. Click here if you missed the very first part of this introduction to NLP: The Bible under the NLP eye (Part 1) The first part of a fun data science project, to learn more about text processing, NLP techniques, and extracting…towardsdatascience.com

This month: Microsoft, INRI and IIIT tackle the brain-computer 💻 interface and Visio-linguistic Transformers to solve the brain encoding problem 🧮 and the very first public graph neural network framework 🕸️ to explore brain structural and functional networks. Support my writing and projects by joining Medium through my referral link: Join Medium with my referral link - Stefano Bosisio As a Medium member, a portion of your membership fee goes to writers you read, and you get full access to every story…stefanobosisio1.medium.com

This month: PDE and deep learning to build up brain’s 🧠 connectome🔗, brain-computer 💻 interface for hand prosthesis and finally a new look at Hidden Markov Models for brain dynamics understanding. Support my writing and projects by joining Medium through my referral link: Join Medium with my referral link - Stefano Bosisio As a Medium member, a portion of your membership fee goes to writers you read, and you get full access to every story…stefanobosisio1.medium.com

The first part of a fun data science project, to learn more about text processing, NLP techniques, and extracting meaningful information from text corpus. — Since Easter is approaching I thought of a nice and fun data science project, applying NLP techniques to the Bible. The Bible can be freely downloaded in text format from the Gutenberg project https://www.gutenberg.org/cache/epub/1581/pg1581.txt (Gutenberg License)