Generative AI, from GANs to CLIP, with Python and Pytorch
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English (US) | Size: 13.10 GB | Duration: 14h 48m
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English (US) | Size: 13.10 GB | Duration: 14h 48m
Generative AI, from GANs to CLIP, with Python and PyTorch is a comprehensive and advanced-level course designed to guide learners through the fascinating world of generative artificial intelligence. The course takes a deep dive into how modern AI systems create images, understand text, and generate new content by exploring core architectures such as GANs (Generative Adversarial Networks), VAEs, and CLIP-based multimodal models. Learners will gain hands-on experience coding AI systems using Python and PyTorch, building models that can generate realistic images, manipulate visual content, and connect textual prompts with visual outputs. The course also explains key theoretical concepts in an intuitive way, helping students understand how neural networks learn representations, optimize latent spaces, and produce creative results. Through step-by-step coding exercises and real-world examples, students develop both theoretical knowledge and practical skills in deep learning and generative AI. This course is ideal for developers, data scientists, machine learning enthusiasts, and anyone looking to build a strong foundation in modern AI systems and creative machine learning applications.
