nn
A Gentle Introduction to AI
Preparing for Generative Pre-trained models
Mon, Thu. 9:25-10:40, 10:50-12:05

Hello everyone! I'd like to invite you to join our course titled "A Gentle Introduction to AI," a preparatory course for Generative Pre-trained models, or GPT models.

No math skills required!

In this course, you will understand the fundamentals of AI, neural networks, and GPT models. You'll learn concepts like the perceptron, supervised learning, and gradient descent.

You'll also get hands-on experience creating and training simple neural networks, and familiarize yourself with using pre-trained GPT models in Python. You'll develop an understanding of tokenization, context, and different types of queries.

Our course is designed for beginners who want to get started with AI and GPT models. While basic knowledge of any programming language is highly recommended, and familiarity with Python programming will be beneficial, no general understanding of artificial intelligence and machine learning concepts is required.

Throughout this course, we'll delve into various topics, ranging from the basics of AI and neural networks, building a micro-network, creating more advanced networks, working with pre-trained GPT models in Python, and finally, practical applications and projects.

In our lab work, you'll apply the concepts you learn in the theory classes by working on practical exercises and mini-projects using Python and GPT models. We encourage students to share their experiences and progress, fostering a collaborative learning environment.

So, if you've ever wanted to dive into the world of AI and neural networks, this is your chance.

Let's explore the possibilities of AI together.

I hope to see you in class soon!

Course Objectives
Understand the fundamentals of AI, neural networks, and GPT models
Learn the concepts of perceptron, supervised learning, and gradient descent
Gain hands-on experience in creating and training simple neural networks
Familiarize yourself with using pre-trained GPT models in Python
Develop an understanding of tokenization, context, and different types of queries

Prerequisites:
Basic knowledge of any programming language is highly recommended. Familiarity with Python programming. This course is designed for beginners who want to get started with AI, specifically focusing on GPT models.
No general understanding of artificial intelligence and machine learning concepts is required

Course Description:

Topics covered in theory classes (subject to change):

Week 1: Introduction to AI and Neural Networks

  • Overview of artificial intelligence and machine learning
  • Neuron model and perceptron
  • Supervised learning and gradient descent

Week 2: Building a Micro-Network

  • Design and implementation of a simple neural network
  • Training the network for a single arithmetic operation
  • Understanding key machine learning concepts: epochs, weights, and learning rate

Week 3: Creating More Advanced Networks

  • Developing slightly more complex neural networks
  • Exploring various network architectures and their applications

Week 4: Working with Pre-trained GPT Models in Python

  • Introduction to GPT-3.5 and GPT-4 APIs
  • Understanding tokenization and context in GPT models
  • Different types of queries and using moderation API

Week 5: Practical Applications and Projects

  • Hands-on exercises and mini-projects using GPT models
  • Exploring potential applications of AI and GPT in various domains

Week 6: Course Review and Final Project

  • Recap of the concepts covered throughout the course
  • Final project: Implementing a practical AI solution using GPT models

Lab Work:
Throughout the course, students will apply the concepts they learn in the theory classes by working on practical exercises and mini-projects using Python and GPT models. They will create simple neural networks, explore various architectures, and learn how to use pre-trained GPT models. Students will be encouraged to share their experiences and progress, fostering a collaborative learning environment.

Comments