A Journey through Generative AI's Frontier Python Libraries
summary
A demo builds a simple GAN and VAE with TensorFlow/Keras, outlines encoder/decoder and generator/discriminator code, and compiles training loops; Hugging Face is used via Hugging Face pipelines for text generation, sentiment and translation with examples of prompting; LangChain appears as LangChain orchestration to glue pretrained LLMs into chatbots and apps; discusses fine‑tuning just the last layers of image models to save compute and notes Transformers can generate images but currently trail GANs in quality.
AI-written summary · about
chapters (10)
- 0:00Introduction and company background
- 1:30What is generative AI
- 3:37Discriminative vs generative models
- 5:04Generative AI model types
- 8:56Building GANs with Python
- 10:23Variational autoencoders in Python
- 11:06Large language models overview
- 12:30Hugging Face Transformers basics
- 15:48LangChain for LLM applications
- 17:57Q&A session
related talks
53mGenerative AI: Overview and use cases
01h 17mDeep generative models for image...
37mHarnessing the power of Generative Adversarial Networks (GANS) for supervised learning
34mGenerative AI Landscape Building a Modern Data Strategy
19mLet's Talk GenAI
18mNavigating the growth frontiers of generative AI
28mGPT or how I learned to stop worrying and love the generative AI
38mBuilding Generative AI Applications in Python with LangChain