Brain Inspired BI 167 Panayiota Poirazi: AI Brains Need Dendrites
Yiota's Path to Dendrites
- Panayiota Poirazi's interest in the brain started in high school, but her home country lacked neuroscience programs.
- She studied mathematics, then biomedical engineering at USC, where she discovered her love for dendrites through Bartlett Mel.
Dendrites and Efficiency
- Brains, unlike current AI, face evolutionary pressure for efficiency due to limited size and energy.
- Dendrites shine in this aspect, optimizing computation and resource use, unlike large, energy-intensive AI models.
Dendrites' Secret Sauce
- While scaling AI might improve cognitive abilities, dendrites may offer a 'secret sauce'.
- This could be linked to perceptual 'aha' moments seen through dendritic activity when perceiving new stimuli.
Support the show to get full episodes, full archive, and join the Discord community.
Check out my free video series about what's missing in AI and Neuroscience
Panayiota Poirazi runs the Poirazi Lab at the FORTH Institute of Molecular Biology and Biotechnology, and Yiota loves dendrites, those branching tree-like structures sticking out of all your neurons, and she thinks you should love dendrites, too, whether you study biological or artificial intelligence. In neuroscience, the old story was that dendrites just reach out and collect incoming signals for the all-important neuron cell body to process. Yiota, and people Like Matthew Larkum, with whom I chatted in episode 138, are continuing to demonstrate that dendrites are themselves computationally complex and powerful, doing many varieties of important signal transformation before signals reach the cell body. For example, in 2003, Yiota showed that because of dendrites, a single neuron can act as a two-layer artificial neural network, and since then others have shown single neurons can act as deeper and deeper multi-layer networks. In Yiota's opinion, an even more important function of dendrites is increased computing efficiency, something evolution favors and something artificial networks need to favor as well moving forward.
- Poirazi Lab
- Twitter: @YiotaPoirazi.
- Related papers
0:00 - Intro 3:04 - Yiota's background 6:40 - Artificial networks and dendrites 9:24 - Dendrites special sauce? 14:50 - Where are we in understanding dendrite function? 20:29 - Algorithms, plasticity, and brains 29:00 - Functional unit of the brain 42:43 - Engrams 51:03 - Dendrites and nonlinearity 54:51 - Spiking neural networks 56:02 - Best level of biological detail 57:52 - Dendrify 1:05:41 - Experimental work 1:10:58 - Dendrites across species and development 1:16:50 - Career reflection 1:17:57 - Evolution of Yiota's thinking