GPU-Powered ML, AI, and Quant Finance with Google Colab (2)

Deep Learning & Generative AI with Google Colab — Session 2 🚀 Train CNNs, run Transformers, chat with a local LLM, and generate images — all on a free Google Colab T4 GPU. In this second session of our free 3-part webinar series, Dr. Yves J. Hilpisch walks through four ready-to-run notebooks that bring deep learning and generative AI to your browser. 📘 Notebooks in this session: 05 — CNN Image Classification: Fashion-MNIST, CPU vs GPU timing 06 — Transformer Time-Series: one-step-ahead forecasting with a compact encoder 07 — Local LLM on Colab GPU: chatting with Qwen2.5 1.5B on a free T4 08 — Stable Diffusion: text-to-image generation with prompt and step-count controls ⚡ Key highlights on a free T4 GPU: • CNN training: ~2x faster than CPU • Transformer forecasting: ~70x faster • Local LLM: ~11 tokens/second • Stable Diffusion: 1-7 seconds per image 🔗 Resources: 📑 Slides: https://tpq.io/tpq_colab_2.pdf 📂 Notebook repo: https://github.com/yhilpisch/colab 📈 CPF: https://cpf.tpq.io 🤖 TAE: https://theaiengineer.dev ₿ TCE: https://thecryptoengineer.dev 📊 TDS: https://thedatascientist.dev 📌 Disclaimer: This content is provided solely for illustration and educational purposes. The Python Quants GmbH is not affiliated with, endorsed by, or sponsored by Google. All numbers and specifications are indicative; always check the official Google Colab documentation for current and reliable information. #GoogleColab #GPU #DeepLearning #CNN #Transformer #LLM #StableDiffusion #Python #GenerativeAI #AIEngineering