Skip to main content

1. Definition

 

1. Definition

1.1. What is Deep Learning?

 

“Deep learning is the state-of-the-art approach across many domains, including object recognition and identification, text understating and translation, question answering, and more. In addition, it is expected to play a key role in many new usages deemed almost impossible before, such as fully autonomous driving”, Ronny Ronen

It looks like a lot of fun, right? I am sure you already know what you need Deep Learning for, which I bet is something fascinating. So without making it longer… Let’s start diving!!

I will try to make this manual as concise and self-explanatory as possible. I still lack of experience so I apologize in advance if there is anything that is not clear or does not work. If you let me know I’ll do my best to improve the explanation or fix the problems as soon as I can.

By the way, in this handeable manual we can find a glossary of terms in the end. I will try to set in italics (or other marking?) everytime a word appears and it is included in the glossary as main definition. Please feel free to navigate through it, report if there is any mistake/missing definition, and constructive comments are more than appreciated.

 

1.2. What is it used for?

 

The main current applications of Deep Learning are:

- Image Recognition: yes, the one Facebook uses to suggest tags in the pictures could be an example

- Natural Language Processing: Google Translate! It is able to recognize & translate whole sentences at a time (sometimes better than others, we should say) instead of word-by-word.

- Visual Art Processing: in order to identify a specific style period of a given painting, for instance.

- Drug Discovery and Toxicology: it can be used to predict biomolecular targets and anticipate toxic effects.

Other applications can be found in:

JASON BROWNLEE - 8 Deep Learning Applications

MEDIUM - 15 Deep Learning Applications

YARON HADAD - 30 Deep Learning Applications

Comments

Post a Comment

Popular posts from this blog

4. Understand how a Neural Network works

4. Understand how a Neural Network works 4.1. Graphical Understanding In order to start in this world, it is important first to have a visual perception of what we are going to deal with, and understand the basics of how Neural Networks work, in the raw form. Image Source A Neural Network (NN) is nothing else than a net of perceptrons that are linked so that input fires another network that produces an output.  Of course, a NN has assigned values that allow to make further calculations and learning.   Image source So far the two images above represent a simple NN with 1 input, 1 output and 1 hidden layer. The hidden layer is said to be dense (each neuron in a layer x is connected to all neurons in the layer x-1 and all the neurons in the layer x+1). Depending on how the neurons are organized and how the connections are made, we can find many different types of NN:   Types of NN (image source and explanation) 4.2. Simple Neural
Post a Comment
Read more

Glossary of terms

  Image Source Machine learning (ML) : Subfield of Artificial Intelligence (AI) in the field of computer science focused on the development of intelligent systems, capable of "learning" (i.e., progressively improve performance on a specific task) with data , without being explicitly programmed. Ref Chronology : Build with GoogleCloud - Chronology tree for ML Perceptron : algorithm for supervised learning of binary classifiers (functions that can decide whether an input, represented by a vector of numbers, belongs to some specific class or not → classification in two parts). “It is a single layer NN”, thus in order to learn how a NN works, we should learn how a perceptron works. Weights : show the strength of the particular node Bias value : allows to shift the activation function Activation function : map input between required values like (0, 1) or (-1, 1).      Fig : Perceptron Deep learning : (also known as deep stru
Post a Comment
Read more