ML Pub Club #31: Beyond LLMs': Spiking networks, neuromorphic computing and lessons from computational neuroscience

​Beyond LLMs': Spiking networks, neuromorphic computing and lessons from computational neuroscience

​LLMs are very capable and useful systems (if used right), but their success has narrowed our picture of what artificial intelligence could be. A model trained by massive-scale backpropagation (in a huge data center) and then largely frozen at deployment is very different from a nervous system that continuously processes temporal signals, adapts locally, and operates under severe energy constraints. In the shadows of the ongoing LLM hype, there is an alternative, much more biologically plausible area of AI research.

​This talk explores the intersection of computational neuroscience, spiking neural networks, and neuromorphic computing, an alternative computing paradigm. We will build a spiking neuron from first principles, examine how networks compute through temporal dynamics, and explore biologically inspired learning mechanisms such as STDP, eligibility traces, neuromodulation, homeostasis, and consolidation. We will then look at neuromorphic hardware, realistic efficiency claims, show a small robot that learns locally without backpropagation and discuss remaining challenges in the field.

​🎤 Lecturer:
Marko Velić - Software Engineer, Google

​Marko Velić is a Software Engineer at Google. Previously he worked at Photomath, Meta (Facebook), Styria, LEGO (as consultant), University of Zagreb and has entrepreneurship experience. He won many awards including the ones from Microsoft and NVIDIA. Marko holds PhD and MBA degrees. He is interested in ML research, computational neuroscience, applied math and practical applications in real life scenarios.

​🗓️ October 7th
🕕 18:00
📍 CroAI HQ, Zavrtnica 17, 4th floor, Zagreb

​🔗 Registrations via Luma: https://luma.com/6762xojz

​If you are curious about what AI might look like beyond the dominant LLM architecture, this session offers a practical introduction to one of the field’s most interesting alternative directions!

​❤️ PS: Stay and hang out with us after the sesh! 💙