Data processing from Machine Learning to Deep Learning

What you will learn

• Introduce the participants to the definition of Machine Learning and its advantages for data processing

• Explain the importance of data in Machine Learning. Present the different types of data and how to explore the data to extract meaningful information.

• Discover the basics of the Python programming language and the main libraries used in the field of Machine Learning for data processing and visualization.

• Define the different categories of Machine Learning models and present some main models with practical examples.

• Introduce the participants to the field of Deep Learning and how it differs from Machine Learning.

• Understand how a neural network learns and what it needs to learn well.

• Learn to tune your neural network and use the right techniques to solve common problems that occur in real applications to ensure better performance.

• Dive into the world of Convolutional Neural Networks (CNN) and how they are used for image classification, object detection, image segmentation, and image generation.

• Introduction to Recurrent Neural Networks and its various applications.

• Discover Tensorflow/Keras, one of the most used Python libraries for Deep Learning and learn how to use it to train your own neural network.

• Several use cases and examples will be presented all along the course for a better understanding of real applications.

Syllabus

Chapter 1: Introduction to Machine Learning

• What is Machine Learning?

• Advantages of Machine Learning

• Types of Machine Learning models

Chapter 2: Data is the key

• Data types

• Exploratory Data Analysis

• Data visualization

• Correlation Analysis and Feature selection

Chapter 3: Introduction to Python for data processing

• Introduction to Python

• Math, Numpy, Matplotlib, Pandas, …

Chapter 4: Introduction to main Machine Learning models

• Machine Learning pipeline

• Linear regression

• Decision Tree

• Random Forest

• k-nearest neighbors

• K-means clustering

• Model validation and evaluation metrics

• Examples of the main Machine Learning models using Python

Chapter 5: Introduction to Neural Networks

• Differences between Machine Learning and Deep Learning

• What is a Neural Network? and how does it learn?

Chapter 6: Convolutional Neural Networks

• Introduction to convolutional neural networks

• Structure and advantages of a convolutional neural network

Chapter 7: Training a Neural Network

• Preparing the dataset and its annotation

• Convergence and overfitting: Is my network learning well?

Chapter 8: Training tips and tricks

• Training techniques: Common problems during the training and how to solve them

Chapter 9: Deep Learning with Python 

• Introduction to OpenCV, Tensorflow and Keras

• MLP model training

• CNN model training

Chapter 10: Convolutional Neural Network for Object Detection

• From Classification to Object Detection: an overview

• Example with Python

Chapter 11: Convolutional Neural Network for Segmentation

• From Classification to Segmentation: an overview

• Example with Python

Chapter 12: Introduction to Generative Adversarial Networks

• Introduction to GANs

• Example with Python

Chapter 13: Introduction to Recurrent Neural Networks

• Recurrent Neural Network

• LSTM

• Attention Mechanism

• Example with Python

Prerequisites

• Basic knowledge in mathematics and algebra 

• Basic level in English

• A PC and notebook

Target learners

• Anyone wishing to start an early career in Machine Learning or Deep Learning

Duration

100 hours in 6 months

Professor in charge

Prof. Karim Tout

Karim TOUT is the Head of AI at uqudo specializing in computer vision and digital identity. He has several years of experience leading AI teams and building AI-based computer vision products across diverse industries. He also provides expert consultancy and professional training on AI at Cetim France and teaches an AI Master course at the French-Azerbaijani University (UFAZ) as an invited professor.