One of the most attractive and widely used fields in the last century is artificial intelligence. There are now many applications for artificial intelligence in the world around us, such as driverless cars, voice assistants, online translators, intelligent robots, diagnostic software, intelligent data mining algorithms, face recognition, speech robots, and more.
Artificial intelligence is a very broad knowledge, part of which is deep learning. Deep learning is one of the hottest and attractive topics that have found a lot of enthusiasts. One reason for this interest is the simplicity of the work and the astonishing results. For example, to recognize an object in an image, if you want to use the old methods, you have to extract the feature and then select a categorizing model. This process is very time-consuming and specialized and a specialist must adjust the type of features and their parameters. But with deep learning, you just need to design the structure of your model and you do not need the feature extraction step and the whole process is done by the layers of the deep learning model.
The next reason for the appeal of deep learning is that there are so many pre-trained models that make the design, training, and testing process so short, and you change a ready-made model for your application according to the concept of transfer learning. This means that you no longer have to invent the wheel from scratch and start all the hard and tedious process of designing your smart model from scratch. There are now pre-trained models that can accurately identify 1000 different images of classes. That means you import the model and give it an image and it does the identification work for you.
Why this package?
Artificial Neural Networks are a simple model from the neural system in the human brain, which have many applications in science and engineering. The most important features of ANN are great capabilities as well as simplicity.
Currently, deep learning models find many applications and are one of the hot topics, so learning of deep learning is one of the necessary things for everyone.
There are many learning resources for deep learning, but most of them are theory-based, and they do not focus on the application side of deep learning.
In this tutorial package, you will learn how to implement and run MATLAB code for different applications. There are many examples in each section for you, to learn better.
We start with basics and continue to advanced, so you will learn step-by-step and you will have the best result.
This package is the result of many years of experience in different deep learning projects.
Common error :
Most of the beginners in MATLAB and deep learning face many errors, when they run or develop code. In this tutorial, we will describe the most common error in the deep learning toolbox of MATLAB.
Many examples :
We collect many examples for you that you can find all of them in any book or learning resource.
Who can use this package :
Everyone that would like to implement code or project in MATLAB
Basic of deep learning
MATLAB coding for Artificial Neural Network (ANN)
Modelling by ANN
Classification by ANN
ANN for Prediction
ANN in Image processing