MONTRÉAL.IA | Intelligence Artificielle Montréal

L’Académie de Montréal.IA


IA 101: Le premier survol complet de l’IA destiné au grand public

Intelligence Artificielle 101 | jeu. 10 oct. 2019 18:00 - 20:30 EDT

IA 101: Le premier survol complet de l’IA destiné au grand public

Un cours de 75 minutes pratique et bien conçu!

You are qualified for a career in machine learning!

Réunissant toutes les facettes de l’IA, le secrétariat général de MONTRÉAL.IA introduit: “Intelligence Artificielle 101 : Un survol complet sur l’IA destiné au grand public“.

PUISSANT ET UTILE. Ce cours est conçu pour offrir à tous l’état d’esprit, les compétences et les outils nécessaires pour percevoir l’intelligence artificielle d’un nouveau point de vue stimulant:

  1. Des découvertes et des connaissances scientifiques de pointe;
  2. Les meilleurs codes et implémentations “open source” ;
  3. L’impulsion qui anime l’intelligence artificielle d’aujourd’hui.

Langage: La présentation sera en français. Le matériel de référence sera dans sa langue originale.

Lieu: NRH Prince Arthur - Ballroom B, 3625 Avenue du Parc, Montreal (Québec), Canada, H2X 3P8.

In life, you need forcing functions. You never know what you’re capable of until you have no choice but go and do it. Excessive comfort leads to unrealized potential.“ — François Chollet

Une liste de codes et implémentations en “open source” confectionnée à titre gracieux:

Montréal.IA est la plus grande communauté IA au Canada. Rejoignez-nous et apprenez tout de l’IA! !

Une liste de codes et implémentations en "open source" confectionnée à titre gracieux

*Cette section est présentée dans sa langue originale anglaise.

The best way to predict the future is to invent it.“ — Alan Kay

0. Getting Started

Today’s artificial intelligence is powerful, useful and accessible to all.

Tinker with Neural Networks : Neural Network Playground — TensorFlow

On a Local Machine
Install Anaconda and Launch ‘Anaconda Navigator
Update Jupyterlab and Launch the Application Under Notebook, Click on ‘Python 3

In the Cloud

In the Browser

Preliminary Readings

Artificial Intelligence 101: The First World-Class Overview of AI for the General Public

1. Deep Learning

DL is essentially a new style of programming–”differentiable programming”–and the field is trying to work out the reusable constructs in this style. We have some: convolution, pooling, LSTM, GAN, VAE, memory units, routing units, etc.“ — Thomas G. Dietterich

1.1 Neural Networks

Neural networks” are a sad misnomer. They’re neither neural nor even networks. They’re chains of differentiable, parameterized geometric functions, trained with gradient descent (with gradients obtained via the chain rule). A small set of highschool-level ideas put together.“ — François Chollet

I feel like a significant percentage of Deep Learning breakthroughs ask the question “how can I reuse weights in multiple places?”
– Recurrent (LSTM) layers reuse for multiple timesteps
– Convolutional layers reuse in multiple locations.
– Capsules reuse across orientation.
“ — Trask

1.2 Recurrent Neural Networks

  • Understanding LSTM Networks — Christopher Olah
  • Attention and Augmented RNN — Olah & Carter, 2016
  • Computer, respond to this email — Post by Greg Corrado
  • Reversible Recurrent Neural Networks — Matthew MacKay, Paul Vicol, Jimmy Ba, Roger Grosse
  • Recurrent Relational Networks Blog | arXiv | Code — Rasmus Berg Palm, Ulrich Paquet, Ole Winther
  • Massive Exploration of Neural Machine Translation Architectures arXiv | Docs | Code — Denny Britz, Anna Goldie, Minh-Thang Luong, Quoc Le
  • A TensorFlow implementation of : “Hybrid computing using a neural network with dynamic external memory” GitHub — Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann, Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield, Phil Blunsom, Koray Kavukcuoglu & Demis Hassabis

1.3 Convolution Neural Network

I admire the elegance of your method of computation; it must be nice to ride through these fields upon the horse of true mathematics while the like of us have to make our way laboriously on foot.“ — A. Einstein

1.4 Capsules

2. Autonomous Agents

No superintelligent AI is going to bother with a task that is harder than hacking its reward function.“ — The Lebowski theorem

2.1 Evolution Strategies

2.2 Deep Reinforcement Learning

2.3 Self Play

AlphaGo Zero : Algorithms matter much more than big data and massive amounts of computation

Self-Play is Automated Knowledge Creation.“ — Carlos E. Perez

2.4 Multi-Agent Populations

2.5 Deep Meta-Learning

2.6 Generative Adversarial Network

What I cannot create, I do not understand.“ — Richard Feynman

2.7 World Models

  • World Models — David Ha, Jürgen Schmidhuber
  • Imagination-Augmented Agents for Deep Reinforcement Learning — Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, Demis Hassabis, David Silver, Daan Wierstra

3. Environments

3.1 OpenAI Gym

3.2 Unity ML-Agents

3.3 DeepMind Control Suite

3.4 Brigham Young University | Holodeck

  • BYU Holodeck: A high-fidelity simulator for deep reinforcement learning Website | GitHub | Documentation — Brigham Young University

3.5 Facebook’s Horizon

  • Horizon: Facebook’s Open Source Applied Reinforcement Learning Platform Paper | GitHub | Blog — Jason Gauci, Edoardo Conti, Yitao Liang, Kittipat Virochsiri, Yuchen He, Zachary Kaden, Vivek Narayanan, Xiaohui Ye

3.6 PhysX

  • PhysX SDK, an Open-Source Physics Engine GitHub | Blog — NVIDIA

4. General Readings, Ressources and Tools

ML paper writing pro-tip: you can download the raw source of any arxiv paper. Click on the “Other formats” link, then click “Download source”. This gets you a .tar.gz with all the .tex files, all the image files for the figures in their original resolution, etc.“ — Ian Goodfellow

Réservation de groupe:

✉️ Courriel :
📞 Téléphone : +1.514.829.8269
🌐 Site web :
📝 LinkedIn :
🏛 Secrétariat Général de Montréal.IA : 350, RUE PRINCE-ARTHUR OUEST, SUITE #2105, MONTRÉAL [QC], CANADA, H2X 3R4 *Conseil exécutif et bureau administratif

#IA101 #IntelligenceArtificielle #IntelligenceArtificielle101 #IntelligenceArtificielleMontreal #MontrealIA

Your browser is out-of-date!

Update your browser to view this website correctly. Update my browser now