Deep Learning and Generative Artificial Intelligence

CNNs, LSTMs, GANs, VAEs, Transformers (including GPTs) and Stable Diffusion

Created by: Luís Cunha, PhD
University Professor

What Will I Learn?

• Learn the basic principles of artificial neural networks and how they are trained.
• Implement and train Convolutional Neural Networks (CNNs) for image classification and object detection using Python.
• Design and apply Long Short-Term Memory (LSTM) networks to predict and analyze time series data.
• Construct, fine-tune, and deploy Transformer models, such as GPT-type models, for various natural language processing tasks.
• Create and train Generative Adversarial Networks (GANs) to generate realistic synthetic images and data.
• Build and utilize Variational Auto-Encoders (VAEs) for data compression and generation tasks.
• Apply style transfer and stable diffusion methods to creatively alter and enhance images.

Requirements

• Basic understanding of programming concepts is recommended, but not required. Familiarity with Python will be helpful for coding exercises. Access to a computer with internet connection for using demos and playgrounds.

Target audience

• This course is designed for anyone interested in deep learning and generative AI, including beginners with no programming experience who want to use AI through user-friendly interfaces, as well as programmers looking to deepen their understanding and skills in this field.