Start Date: 16/07/2023
Course Overview
Machine learning is the science of getting computers to act without being explicitly programmed. It’s a sub disciplinary of a broader field calls Artificial Intelligence (AI). In this course we’ll cover all the aspects of this amazing field: from the theories & techniques to daily industrial challenges, to solving the most common problems. We’ll also cover the most popular libraries & tools (mostly Python language based) for implementing all the ML model lifecycle.
Prerequisite:
- Gmail account in order to be able to use Google Colab development tool.
- Basic knowledge of Linear Algebra, Statistics and Calculus.
- Basic Python programming skills:
- Basic Python syntax: This includes understanding how to write and structure code in Python, including how to use variables, functions, and control structures.
- Data types and data structures: It is important to understand the different data types that Python supports (such as integers, floats, strings, and lists) and how to work with them. The participants should also be familiar with more advanced data structures such as dictionaries and sets. Understanding the basic concept of classes is highly recommended.
- Working with libraries: The participants should be familiar with how to import and use libraries in Python, particularly libraries for scientific computing (such as NumPy), data analysis (such as pandas), and data visualization (such as matplotlib)
Skills Gained: After completing this training, you will be able to:
In this AI course, we will learn the basics of machine learning using deep learning algorithms with the help of ChatGPT. Some of the genera machine learning topics that will be covered include:
- Basic machine learning concepts: We will learn about the different types of machine learning and the concepts that are important for understanding how they work, such as supervised and unsupervised learning, model evaluation, and overfitting.
- Data cleaning and preparation: Before we can build machine learning models, we need to make sure that our data is in a suitable format. We will learn about techniques for preprocessing and cleaning data, including how to handle missing values, merge data sets, and convert data types.
- Data visualization: Visualizing data is an important part of the data analysis process, and we will learn how to use Python’s data visualization libraries to explore and communicate insights from our data.
- Version control: In this course, we will also learn about version control systems and how they can be used to track changes to our codebase. This is particularly important in collaborative projects where multiple people are working on the same codebase.
Course Outline:
Day 1
Lecture 1: Perceptron and IDE – In this lecture, we will learn about the perceptron algorithm, which is a fundamental building block of neural networks. We will also learn about integrated development environments (IDEs) and how they can be used to write and run code.
Lecture 2: Manually Establishment and analysis NN – In this lecture, we will learn how to build and analyze neural networks manually, without the use of libraries or frameworks.
Lecture 3: Full connection NN for clothing classification MNIST – In this lecture, we will learn how to build and train a full connection neural network for clothing classification using the MNIST dataset.
Day 2
Lecture 4: CNN Clothing Classification – Gray Levels Images – In this lecture, we will learn how to build and train a convolutional neural network (CNN) for clothing classification using grayscale images.
Lecture 5: CNN Clothing Classification – Color Images – In this lecture, we will learn how to build and train a CNN for clothing classification using color images.
Lecture 6: TENSORS – In this lecture, we will learn about tensors and how they are used in machine learning. We will also learn about singular value decomposition (SVD) and how it can be used to analyze data.
Day 3
Lecture 7: Exploratory Data Analysis (EDA) confusion matrix AUC histogram – In this lecture, we will learn about exploratory data analysis (EDA) and how it can be used to understand and visualize data. We will also learn about the confusion matrix, AUC, and histograms and how they can be used to evaluate machine learning models.
Lecture 8: ResNet VGG GoogleNet MobileNet – In this lecture, we will learn about some of the most widely used convolutional neural network architectures, including ResNet, VGG, GoogleNet, and MobileNet.
Lecture 9: Upsampling and UNet – In this lecture, we will learn about upsampling and how it can be used in image processing. We will also learn about the UNet architecture and how it can be used for image segmentation. All rights reserved to Yoram Segal 4
Day 4
Lecture 9: Up sampling and UNet – In this lecture, we will learn about upsampling and how it can be used in image processing. We will also learn about the UNet architecture and how it can be used for image segmentation.
Lecture 10: YOLO – In this lecture, we will learn about the YOLO (You Only Look Once) algorithm and how it can be used for object detection.
Day 5
Lecture 11: GAN – In this lecture, we will learn about generative adversarial networks (GANs) and how they can be used to generate new data.
Lecture 12: NST CycleGan – In this lecture, we will learn about neural style transfer (NST) and CycleGAN and how they can be used to manipulate images and video.