Workshop Overview
This workshop is designed for mathematics instructors who want to understand and teach the connections between calculus concepts and modern artificial intelligence systems. By exploring how mathematical principles like the chain rule, partial differentiation, and gradients are applied in neural networks, you'll be equipped to show students the real-world relevance of the mathematics they're learning.
Throughout this website, you'll find detailed explanations, visualizations, code examples, and teaching resources that will help you understand and communicate these connections effectively.
Mathematical Foundations
Explore how the chain rule, partial differentiation, and gradients form the mathematical foundation of deep learning.
Learn More
Neural Networks
Understand the architecture of neural networks and how data flows through them during forward propagation.
Learn More
Training Neural Networks
Discover how backpropagation and gradient descent use calculus to train neural networks.
Learn MoreWhy Mathematical Concepts Matter in AI
Artificial intelligence, particularly deep learning, is built upon a foundation of mathematical concepts that are taught in standard calculus and linear algebra courses. Understanding these connections can help mathematics instructors:
- Show students the real-world applications of abstract mathematical concepts
- Motivate the study of calculus by connecting it to cutting-edge technology
- Prepare students for careers in AI, data science, and other technical fields
- Develop interdisciplinary projects that connect mathematics to computer science
- Stay current with how mathematics is being applied in industry and research
This workshop bridges the gap between theoretical mathematics and its practical applications in AI systems, providing you with the knowledge and resources to bring these connections into your classroom.
Practical Applications
The workshop includes practical code examples and implementations that demonstrate the mathematical concepts in action. These examples are designed to be accessible to mathematics instructors who may not have extensive programming experience.
A neural network learning the XOR function, which is not linearly separable
By working through these examples, you'll gain a deeper understanding of how mathematical concepts are implemented in code and how they contribute to the functionality of neural networks.
Explore Code ExamplesTeaching Resources
The workshop provides a variety of teaching resources that you can use to incorporate AI applications into your mathematics courses. These resources include:
Project Ideas
Engaging projects that help students apply mathematical concepts to AI problems.
Classroom Activities
Interactive activities that demonstrate the connection between calculus and deep learning.
Further Learning Resources
Books, online courses, and videos for continued exploration of these topics.
These resources are designed to help you bring the connections between mathematics and AI into your classroom in a way that engages and inspires your students.
Explore Teaching ResourcesKey Takeaways
By the end of this workshop, you will understand:
- How the chain rule enables the backpropagation algorithm in neural networks
- How partial derivatives and gradients guide the optimization process in training
- How mathematical concepts scale up to handle the complexity of modern AI systems
- How to incorporate these connections into your teaching to make mathematics more relevant and engaging
- How to use code examples and visualizations to illustrate these concepts for your students
These insights will equip you to show your students the power and relevance of mathematics in the age of artificial intelligence.