Ramin Hasani

A 1mm-long nematode worm is the world’s best understood animal and with a simple brain of only 302 nerve cells, it can produce complex behavior that current artificial intelligence (AI) systems cannot. Ramin and his team is investigating the nervous system of the C. elegans worm from a machine learning perspective, as an ideal instance of the Simplexity concept, to create simple and transparent AI agents for the control of complex tasks. More information on http://www.tedxvienna.at Ramin is a PhD research assistant in Computer Science at TU Wien, Austria, where he works on developing interpretable artificial intelligence (AI) algorithms for real-world applications. By bringing insights from neuroscience to machine learning he is improving the functional transparency and robustness of AI systems. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at http://ted.com/tedx

Ramin Hasani takes us on a journey inside an artificial neural network. Although artificial neural networks are very good pattern recognition devices, intelligence is more than that, it’s about modeling the world with increased precision. But AI it’s changing the way technology advances.

Liquid neural networks are a class of AI algorithms that can learn to stay adaptable even after training. Liquid neural networks are inspired by how brain cells communicate with each other. They are robust to perturbations, they do not need to be large to generate interesting behavior, and show promise in learning necessary skills from data to perform well beyond their training data. Liquid neural networks have the potential to alleviate many sociotechnical challenges of large-scale machine learning systems, such as interpretability, accountability, fairness, and carbon footprint.

Explore the fascinating journey of AI's rapid progression, diving into the world of generalist AI systems like ChatGPT, GATO, and Liquid Neural Networks. Learn how these powerful tools are changing the game and revolutionizing the way we approach complex problems in finance and robotics. AI, Algorithm, Engineering, Finance, Imagination, Math, Robots

What if AI could think and adapt like a real brain? TED Fellow and AI scientist Ramin Hasani shares how liquid neural networks — a new, more flexible AI technology inspired by physics and living brains — could transform how we solve complex problems.

TED Fellow and AI scientist Ramin Hasani explores a new paradigm in artificial intelligence: liquid foundation models, AI systems inspired by the brain and designed to unlock greater performance while consuming far less energy than traditional models.