Réseaux de neurones (NN)
Les réseaux de neurones sont l'une des découvertes les plus importantes de l'histoire.
Les réseaux de neurones peuvent résoudre des problèmes qui ne peuvent pas être résolus par des algorithmes :
- Diagnostic médical
- Détection facial
- Reconnaissance vocale
Les réseaux de neurones sont l'essence même du Deep Learning .
La révolution de l'apprentissage en profondeur
La révolution de l'apprentissage en profondeur est là !
La révolution de l'apprentissage en profondeur a commencé vers 2010. Depuis lors, l'apprentissage en profondeur a résolu de nombreux problèmes "insolubles".
La révolution de l'apprentissage en profondeur n'a pas commencé par une seule découverte. Cela s'est plus ou moins produit lorsque plusieurs facteurs nécessaires étaient prêts :
- Les ordinateurs étaient assez rapides
- Le stockage informatique était assez grand
- De meilleures méthodes de formation ont été inventées
- De meilleures méthodes de réglage ont été inventées
Neurones
Les scientifiques s'accordent à dire que notre cerveau compte environ 100 milliards de neurones.
Ces neurones ont des centaines de milliards de connexions entre eux.
Crédit image : Université de Bâle, Biozentrum.
Neurons (aka Nerve Cells) are the fundamental units of our brain and nervous system.
The neurons are responsible for receiving input from the external world, for sending output (commands to our muscles), and for transforming the electrical signals in between.
Neural Networks
Artificial Neural Networks are normally called Neural Networks (NN).
Neural networks are in fact multi-layer Perceptrons.
The perceptron defines the first step into multi-layered neural networks.
The Neural Network Model
Input data (Yellow) are processed against a hidden layer (Blue) and modified against another hidden layer (Green) to produce the final output (Red).
Neural Networks with JavaScript
Artificial Intelligence can be math-heavy. The nature of neural networks is highly technical, and the jargon that goes along with it tends to scare people away.
This is were JavaScript can come to help. We need easy to understand software APIs to simplifying the process of creating and training neural networks.
JavaScript Libraries
Brain.js
Brain.js is a JavaScript library that makes it easy to understand Neural Networks because it hides the complexity of the mathematics.
Building a neural network with Brain.js.
Introduction to ml5.js
ml5.js is trying to make machine learning more accessible to a wider audience.
The ml5 team is working to wrap machine learning functionality in friendlier ways.
The example below uses only three lines of code to classify an image:
<img id="image" src="pic1.jpg" width="100%">
<script>
const classifier = ml5.imageClassifier('MobileNet');
classifier.classify(document.getElementById("image"), gotResult);
function gotResult(error, results) { ... }
</script>
Try substitute "pic1.jpg" with "pic2.jpg" and "pic3.jpg".
TensorFlow Playground
TensorFlow Playground is a web application written in d3.js.
With TensorFlow Playground you can learn about Neural Networks (NN) without math.
In your own Web Browser you can create a Neural Network and see the result.
TensorFlow.js was previously called Tf.js and Deeplearn.js.
Tom Mitchell
Tom Michael Mitchell (born 1951) is an American computer scientist and University Professor at the Carnegie Mellon University (CMU).
He is a former Chair of the Machine Learning Department at CMU.
E: Experience (the number of times).
T: The Task (driving a car).
P: The Performance (good or bad).
Stories
Giraffe
In 2015, Matthew Lai, a student at Imperial College in London created a neural network called Giraffe.
Giraffe could be trained in 72 hours to play chess at the same level as an international master.
Computers playing chess are not new, but the way this program was created was new.
Smart chess playing programs take years to build, while Giraffe was built in 72 hours with a neural network.