Learn fundamental concepts of Neural Networks, Deep Learning, and Generative Adversarial Networks (GAN) and experience in practice techniques such as face and object detection, style transfer, segmentation, and image generation.
In this intermediate-level course, we will first understand the workings of a Neural Network - a class of algorithms that enables a great deal of development in the field of Machine Learning and Artificial Intelligence. We will talk specifically about Convolutional Neural Networks that operate with images, and learn about techniques for Face and Object Detection, Style Transfer, Adversarial Generative Networks, and Semantic Segmentation, doing practical exercises. Finally, we will try Midjourney, as a generator of novel images from text.
As a final project, there will be several experimental exercises using different neural network models with discussions on applications.
No prior technical knowledge is required, but it is recommended that you have taken the course "Beginning Machine Learning for Artists".
For this course it is recommended that you have a computer or notebook with reasonable settings to run graphical applications and a good internet connection. It is not necessary to install any software beforehand.
Sergio Venancio is a master and doctoral candidate in Visual Arts at ECA USP, Bachelor in Computer Science and in Visual Arts at UNICAMP. Professor at the INTELI Institute of Technology and Leadership, in the Graphic Design Specialization course – IA UNICAMP and in the Post-Graduation in Digital Architecture and Parametric Projects at Belas Artes SP. His research relates to the intersection between Visual Arts and Artificial Intelligences, experimenting with new forms of interactivity based on computer vision models, and producing software that simulates artistic actions, such as observational drawing.