Stanford Online’s Post

Thrilled to share I’ve obtained a new certification: "XCS236 - Deep Generative Models" from Stanford Online! This was the most challenging course I've ever taken. We started with Autoregressive models (familiar territory), but quickly moved through Variational Autoencoders (VAEs), Flow Models, Generative Adversarial Networks (GANs), Energy Based Models, Score Based Models, and culminated with Diffusion Models. Went even deeper into PyTorch coding an Autoregressive GPT-2 Transformer, a few flavors of VAE (vanilla, mixture of gaussians, IWAE, and semi-supervised), a Masked Autoregressive Flow model (MAF), and a few flavors of GAN (vanilla, conditional, and Wasserstein). #genai https://lnkd.in/gPj22c2r

And Stanford's Artificial Intelligence Professional Program is finally complete. An exhaustive and deep walk through the foundational ideas and latest research in AI. I distinctly remember two moments, one with deep reinforcement learning and one with deep generative learning, in which I was lost somewhere between calculus, algebra and probability and wondering whether I really needed to do this... but both times I managed to get as deep as required. I'm not going to say the fake "I'm humbled", no... I'm proud of having done this! And I recommend it to those which are not scared of complex ideas (no simplification or shortcuts are offered in these courses), have strong mathematical foundations and don't mind investing a quite big portion of their spare time. Then it's easy. And the coding is easy once you understand the concepts well. Algebra is so powerful that makes your code fly through numpy! I’m happy to share that I’ve obtained a new certification: Artificial Intelligence from Stanford Online!

I am pleased to announce the successful completion of the Stanford Professional Certificate Program, having completed three rigorous and intellectually rewarding courses: 📘 XCS224N - 010: Natural Language Processing with Deep Learning Explored cutting-edge models and techniques in NLP, including transformers, BERT, and GPT. 📘 XCS224U - 012: Natural Language Understanding Developed a deep understanding of the principles and applications of NLU, including tasks such as sentiment analysis, entity recognition, and question answering. 📘 XCS236 - 003: Deep Generative Models Gained proficiency in advanced generative models, including VAEs, GANs, autoregressive models, normalizing flows, and energy-based models. These courses provided a solid foundation in both the theoretical and practical aspects of natural language processing, natural language understanding, and deep generative models. The program's emphasis on hands-on assignments and real-world applications has significantly enhanced my capabilities in AI and machine learning. I am excited to leverage the knowledge and skills acquired through this program to contribute to advancements in the field of artificial intelligence. Thank you to Stanford University and the instructors for providing such a transformative educational experience.