How sparse neural connections 🖇️ influences functional behavior? A more biological plausible backpropagation: error-vector broadcasting 📡, and how does attention work⚡⚡⚡?

Image by Domink Lange from Unsplash

Why should you care about Neuroscience?

Neuroscience is the root of nowadays artificial intelligence 🧠🤖. Reading and being aware of the evolution and new insights in neuroscience not only will allow you to be a better “Artificial Intelligence” guy 😎, but also a finer neural network architectures creator 👩‍💻!

Here today 3 new papers from arxiv.org. The first one investigates the sparsity connectivity and its influence on functional modularity. The second article proposes a new methodology to back propagation, which may be more biologically plausible — definitely, a lot of research should be devoted here. …


In this tutorial: can we have pandas in Rust? What is smartcore?

Image by Cloris Ying on Unsplash

Welcome back to the third tutorial on Rust and its application for ML! Today we’ll learn Polars a fantastic Rust package to deal with dataframes and series and smartcore, which will be one of our best ML Rust friend :)


How AutoML works? and how can we deploy models on different devices? A look at NAS and recent advances from Google Brain: BigNAS

Image from Unsplash by beasty

When I was learning and get my hands dirty in machine learning, I always wondered how Google AutoML was able to pick up a suitable model for a given task, returning promising and encouraging metric results. Studying more and more, I was happy and excited when I found out the power of Neural Architecture Search (NAS), the key for creating new models, which is run underneath AutoML.

If on one side we have Deep Learning, which could be seen as a successful example of automating feature engineering — namely we do not have to spend hours for finding promising features…


In this tutorial: How to read a csv file in Rust? How to implement a Linear Regression? Let’s get our hand dirty and learn more about rusty_machine.

Image from Unsplash by Clark Van Der Beken

Welcome to the very first tutorial to learn Rust and apply this fantastic programming language to Machine Learning.

What will you learn at the end of…


This is the first part of a series of tutorials on Rust and ML. Today let’s understand 5 basic things about Rust!

Rust and Fungi from Unsplash. Image by Sandra Frey

This tutorial wants to be different from the classical ones. We will not start with a long nomenclature of Rust commands or how to declare variables or how to write hello world etc. Instead, we will start look at 5 important concepts of Rust here, and then, in the next tutorial, we will directly move on get our hands dirty and learn immediately Rust with applications in Machine Learning. It may be hard at first, as there is…


Three questions for May 2021: what is intelligence? 🧠 what is the effect of oxytocin on the brain? 🫂 is the nervous system an optimal structure?🕸️

What is intelligence? noise? blurred spikes dynamics? Image by Meagan Carsience on Unsplash

Why should you care about Neuroscience?

Neuroscience should be seen as the root of artificial intelligence 🧠🤖. Reading and being aware of discoveries in neuroscience not only will allow you to be a better “Artificial Intelligence” pro 😎, but also a finer neural network architecture creator 👩‍💻!
This month we have three papers from the neuroscience world that link to AI. The first poses interesting questions about what intelligence is and if a new definition of intelligence could make AI cooperate with computational neuroscience and get to a more solid theory ground. The second paper applies Machine Learning models to detect…


Is Instagram safe for kids? Learn more about the worrying content I found in my investigations

Instagram from Unsplash. Image by Solen Feyissa.

Instagram is one of the most used social media nowadays, with a total of 1 billion users, 500 million of them active and with millions of shops and brands, which spend about 20% of their marketing budget on this platform. Although these numbers sound great and make us think of Instagram as a safe and secure social media, there have been many warnings and reports highlighting that almost the 50% of all the Instagram accounts may be fake and scam.

Just scrolling through some…


MIT and synaptic reinforcement 🎰, neural tuning and representational geometry 🏗 and cortical neurons as Bayes best friends 🤝👊

Image by Martin Adams on Unsplash

Why you should care about Neuroscience?

Neuroscience is the root for nowadays artificial intelligence 🧠🤖. Reading and being aware of the evolution and new insights in neuroscience not only will allow you to be a better “Artificial Intelligente” guy 😎, but also a finer neural network architectures creator 👩‍💻!

Here I am enlisting 3 papers which are worth to read this month, which deal with neurons and cognitions. The first shades light on neural dynamics, which maybe helpful for you to develop new Markov-chain based Neural Networks. The second is a fantastic review about the maths underneath neural coding and…


This month: Facebook AI vs brain signals 👍, dendritis in artificial neural networks 🚨, understanding illusions in retina dynamics 👁️

Image by Federico Beccari on Unsplash

Deep recurrent Encoder: A scalable end-to-end network to model brain signals

Omar Chehab, Aleandre Defossez, Jean-Christophe Loiseau, Alexandre Gramfort, Jean-Remi King, Paper, Code

This paper comes directly from a collaboration between Facebook AI Research, the University Paris-Saclay and Ecole Normal Superieure. The main key of the paper is to devise a new method to help the neuroscience community to analyse brain responses to sensory inputs. …


Every day hundreds of pre-reviewed papers are published on arxiv.org Stay updated with me, with this mini guide about the most interesting papers for each month. The most peculiar papers for February 2021

The brain. Image by Alina Grubnyak on Unsplash

Neuroscience is the root for nowadays artificial intelligence 🧠🤖. Reading and being aware of the evolution and new insights in neuroscience not only will allow you to be a better “Artificial Intelligente” guy 😎, but also a finer neural network architectures creator 👩‍💻!

February 2021 has 3 interesting papers which are worth a read, here I summarize and convert them to layman terms

The geometry of information coding in correlated neural populations

Rava Azeredo da Silveira…

Stefano Bosisio

Machine Learning Engineer, PhD in Computational Chemistry. My writing covers neuroscience research, coding tutorial and social-media analyses

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store