Blog

Transformers in Pytorch from scratch for NLP Beginners

Wed, 17 Feb 2021 21:12:46 GMT

Everything you need in one python file, without extra libraries Two weeks ago, I wanted to understand Transformers. I read the original paper, I read articles I could find online, I listened to podcas...

Lire Medium

Lire

Why do we close nuclear reactors?

Sun, 02 Apr 2023 22:23:52 GMT

Nuclear reactors may be closed for four main reasons: they reached their end of life, they had an accident, they had technical problems and couldn’t be repaired, or a political decision made them cl...

Lire Medium

Lire

How many people died because of the Chernobyl disaster?

Sun, 02 Apr 2023 18:29:33 GMT

Several studies and organizations investigated deaths related to the Chernobyl accident. I present their results. This article is part of a series on the DEC Report. The DEC report is a 200+ pages fr...

Lire Medium

Lire

Energy, EROI and limits to growth

Sun, 02 Apr 2023 14:07:27 GMT

What is the limit to the amount of energy we can produce? Is EROI the best metric for future constraints? Let’s see! In this article, I provide a simple algorithm to evaluate if a strategy is credi...

Lire Medium

Lire

How much fossil fuel do we consume each year?

Sun, 02 Apr 2023 11:58:25 GMT

Can we really grasp how much fossil fuels we consume each year? Is it a lot? Not that much? Can we easily do an energy transition for climate change? Or is our consumption of fossil fuel so fundamenta...

Lire Medium

Lire

How I assessed the global potential of nuclear energy

Sat, 01 Apr 2023 20:08:49 GMT

This article is part of a series on the DEC Report. The DEC report is a 200+ pages freely accessible report I wrote on climate change and energy. It assesses the world’s potential to tackle climate ...

Lire Medium

Lire

How I evaluated the world’s potential for wind energy

Sat, 01 Apr 2023 17:46:21 GMT

This article is part of a series on the DEC Report. The DEC report is a 200+ pages freely accessible report I wrote on climate change and energy. It assesses the world’s potential to tackle climate ...

Lire Medium

Lire

How I evaluated the world’s potential for solar energy

Sat, 01 Apr 2023 16:28:55 GMT

This article is part of a series on the DEC Report. The DEC report is a 200+ pages freely accessible report I wrote on climate change and energy. It assesses the world’s potential to tackle climate ...

Lire Medium

Lire

How I evaluated the world’s potential for hydroelectricity

Sat, 01 Apr 2023 15:09:34 GMT

This article is part of a series on the DEC Report. The DEC report is a 200+ pages freely accessible report I wrote on climate change and energy. It assesses the world’s potential to tackle climate ...

Lire Medium

Lire

How I built an AI Image Enhancer

Sat, 01 Apr 2023 02:06:01 GMT

What is a great image? It’s just the previous image with more contrast and saturation, right (/s) ? But at some point, the contrast or saturation is too high. And what if the creator of the image d...

Lire Medium

Lire

[Video] A Model for Language Acquisition

Wed, 26 Jan 2022 22:54:31 GMT

In this video I introduce the prototype for language acquisition in the global Artificial General Intelligence project. https://medium.com/media/9a72c93624362c8105f1406f16ee1817/href The model I used...

Lire Medium

Lire

Simulons des pandémies

Thu, 22 Oct 2020 11:56:53 GMT

Propagation d’un virus dans une population Cet article a pour but de transmettre un retour d’expérience sur la simulation de pandémies. Objectif? Comprendre les limites et l’intérêt de ces a...

Lire Medium

Lire

Neural Network in C++ From Scratch and Backprop-Free Optimizers

Tue, 13 Oct 2020 23:03:00 GMT

In this article I’ll present a beginner-oriented framework implementing neural networks in C++. The main goal of this code is to understand the root of neural networks for beginners, it also allows ...

Lire Medium

Lire

A more parameter-efficient SOTA bottleneck! (2020/07)

Sat, 25 Jul 2020 19:40:43 GMT

Linear Bottleneck with Efficient Channel Attention instead of Squeeze Excitation CNN are great blablabla… Let’s get to the point. SOTA for image classification on Imagenet is EfficientNet with 88....

Lire Medium

Lire

Visuels de l’apprentissage des réseaux de neurones

Wed, 03 Jun 2020 19:07:53 GMT

Modification des représentations internes d’un réseau de neurones en cours d’entrainement 1. Le formalisme de l’apprentissage automatique L’apprentissage automatique est la science regroupan...

Lire Medium

Lire

Construire un serveur de Deep Learning en 2020

Sat, 16 May 2020 12:43:19 GMT

[UPDATE 2020/10/03: Prise en compte des nouveaux GPUs de Nvidia] L’intelligence artificielle, à travers l’apprentissage profond, est une discipline bien établie. Les algorithmes utilisés progr...

Lire Medium

Lire