Michal works as a data researcher and software architect for Intel. He is also a chairperson of the Operators group of the open source ONNX (Open Neural Network Exchange) project.
Neural networks have revolutionized AI, enabling machines to learn from data and make intelligent decisions. In this talk, we'll explore two popular architectures: Attention models and Diffusion models.
First up, we'll discuss Attention models and how they've contributed to the success of large language models like ChatGPT. We'll explore how the Attention mechanism helps GPT focus on specific parts of a text sequence and how this mechanism has been applied to different tasks in natural language processing.
Next, we'll dive into Diffusion models, a class of generative models that have shown remarkable performance in image synthesis. We'll explain how they work and their potential applications in the creative industry.
This is a good talk for visual learners. I prepared schematic diagrams, which present main features of the nerual network architectures. By necessity, the diagrams are oversimplified, but I believe they will allow you to gain some insight into Transformers and Latent Diffusion models.