Introduction to AI

Arm Education via edX

Go to class Write review

Details

Go to class

Provider

edX
Pricing

Free Online Course (Audit)
Languages

English
Certificate

$49.00 Certificate Available
Duration & workload

12 weeks, 1-2 hours a week
Sessions

On-Demand
Subtitles

English

Found in

Overview

Are you curious about how artificial intelligence (AI) really works? Wondering which models power these systems, and how they impact society and the environment? Presented by engineers from Arm, this course offers a comprehensive introduction to AI, machine learning, and data science—shedding light on their historical evolution, current capabilities, and potential future developments.

By exploring both the technical concepts and the broader ethical, social, and environmental dilemmas, you will gain a well-rounded understanding of AI’s potential and challenges. You’ll discover how AI, machine learning, and data science interrelate; understand the fundamental algorithms, models, and frameworks; and learn how to apply these concepts in real-world scenarios. The course also addresses the pressing issue of energy consumption in AI.

Key Topics Covered

The turbulent history of AI and its evolution into today’s powerful technology
How AI, machine learning, and data science fit together , including their definitions, examples, and interrelationship
Current and potential future applications of AI in various industries
Fundamental machine learning concepts , including classifiers, linear regression, and neural networks
Training, validation, and test data : how to prepare and evaluate machine learning models
Optimizers and loss functions : building blocks for fine-tuning your models
Ethical and social considerations : exploring AI’s benefits, challenges, and the importance of responsible development
Power consumption vs. sustainability : balancing performance and efficiency with environmental impact
Practical frameworks , such as PyTorch, for implementing and training ML models
AI in the cloud and on the edge : deploying AI across diverse platforms and computing environments

The course culminates with a hands-on capstone project using the PyTorch framework and the CIFAR-10 dataset, allowing you to apply newly acquired skills to a real-world image classification challenge. Whether you’re a budding data scientist, a developer looking to integrate AI into your projects, or simply an AI enthusiast, this course offers both the foundational knowledge and practical skills needed to excel in the rapidly evolving world of artificial intelligence.

Syllabus

Module 1: Introduction to Artificial Intelligence

In this first module you will explore the history of AI, as well as current and potential future developments in the technology.

Module 2: AI and Machine Learning

In this module you will dive into the basic concepts behind machine learning, focusing on key algorithms, models, and linear regression.

Module 3: What's in the Black Box? Deep Learning and Neural Networks

During this module you will study the architecture of neural networks. You will then apply your learning to examine the MNIST dataset using an Artificial Neural Network (ANN).

Module 4: Training and Evaluating Models

In this module you will build an understanding of training, validation, and test data. You’ll learn the difference between overfitting and underfitting, as well as how to identify and address them. You’ll also explore optimizers and loss functions. You will then apply your learning to the MNIST dataset by training and evaluating a machine learning model, then adjusting parameters to classify images. The module concludes with a critical look at balancing power consumption, performance, and sustainability.

Module 5: Advanced Topics in AI

In this module you will compare and contrast Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). You will build an understanding of ‘back propagation’, ‘feed forward’, and predictions. You will also learn about BERT and GPT as examples of transformers. Finally, you’ll delve into the PyTorch framework and find out how it is used for AI and ML applications.

Module 6: Challenges and the Future of AI

In this final module you will discuss AI in the cloud and AI at the edge: the benefits and challenges of each, and their uses. The course finishes with an opportunity for you to get hands on with machine learning, by carrying out a capstone project using the PyTorch framework and the CIFAR-10 dataset.