The Eye in AI: Understanding Image Recognition

General description

Imagine teaching a computer to see like you do. It's not science fiction anymore, it's the reality of AI image recognition. This summer, we're offering you a unique chance to demystify this powerful technology and learn how to wield its potential.

Whether you're just starting your journey in AI or already have some experience, this course is designed to guide you through the fascinating world of image recognition.

We’ll explore the core concepts, dissect real-world applications, and get hands-on with the tools that make it all possible. Get ready to transform your understanding of how machines "see" and interact with the visual world.

But this event is about more than just code; it’s about connecting with amazing people in the heart of Denmark. Picture yourself, brainstorming with other students from Europe, sharing your ideas over a hyggelig coffee break and Danish pastry. Imagine exploring Copenhagen by bike (like a true Dane) and creating unforgettable memories with everyone.

So are you ready to see the world through the eyes of AI, while experiencing the magic of Copenhagen? Then join us for “The Eye in AI” this summer and let’s unlock the potential of AI together.

P.S. No matter how important academics are, we value the same for building connections with people :)

Academic information

Fields of activity:

Computational Sciences , Computer Engineering , Computer Science/Automatic Control/Informatics

Content and topics:

Fundamentals of Digital Images: Understanding image representation, basic image processing techniques (filtering, transformations), and color spaces.
Introduction to Computer Vision: Exploration of core computer vision tasks, including edge detection, feature extraction, and object recognition.
Machine Learning Basics for Image Recognition: Foundational concepts of supervised, unsupervised, with a focus on their relevance to image analysis.
Basics of Deep Learning for Image Recognition: In-depth exploration of neural networks, convolutional neural networks (CNNs), and their architectures for image classification, object detection, and image segmentation.
Practical Applications of Image Recognition: Examination of real-world case studies across diverse fields, such as medical imaging, autonomous driving, surveillance, and creative applications.
Hands-on Projects and Labs: Extensive practical sessions where participants will implement image recognition algorithms using popular programming languages (e.g., Python) and libraries (e.g., PyTorch, PyTorch Lightning).
Importance of Model’s Data: Understanding the impact of dataset quality, size, and biases on model performance, exploring data augmentation techniques, and addressing common data-related issues in AI image recognition.

Learning goals and objectives:

• Understand the fundamental principles of image representation and processing.
• Grasp the core concepts of computer vision and its applications.
• Apply machine learning techniques for image recognition tasks.
• Design and implement basic deep learning models for image analysis.
• Understand the critical role of data in AI models and how data quality impacts model performance.
• Identify and address common data-related issues, including bias, in the context of image recognition.
• Implement data augmentation techniques to improve model robustness.
• Identify appropriate algorithms and techniques for specific image recognition challenges.
• Evaluate the performance of image recognition models.
• Develop practical skills in using Python and relevant libraries for image processing and AI.

Examination type:

Group project or presentation

ECTS credits issued:

1.0

Information for applicants

Selection criteria:

Motivation letter, interest in the topic, and answers to our questions.

Practical arrangements

All of the following are covered by the event fee:

Lodging:

Accommodation provided by the university.

Meals:

Three meals per day, at least one of them warm.

Transportation:

Public transportation provided at no extra costs.