Artificial networks learn to smell like the brain
Nov 2021, phys.org
No kidding, the sensory apparatus that resembles a deep learning neural network can be simulated with a deep learning neural network -- "Artificial networks trained to classify odor identity recapitulate the connectivity inherent in the olfactory system."
The part of our brain that smells is also the most primitive. Before brains were a thing, bacteria performed chemosensory calculations on the primordial soup. As the soup became more complex, so did sensory equipment. Chemosensitive receptors on the surface of a bacterium became antennae, and then became noses, and those noses became seeing, hearing, even speaking brains. But the first version is the one used for smelling. So it shouldn't be a surprise that the first place we see a direct link between the mammalian brain and our artificial instantiation is via olfaction. Nonetheless, the scientists were "surprised to see it replicate biology's strategy so faithfully."
"By showing that we can match the architecture very precisely, I think that gives more confidence that these neural networks can continue to be useful tools for modeling the brain," says Robert Yang, assistant professor in MIT's departments of Brain and Cognitive Sciences and Electrical Engineering and Computer Science [and who collaborated on this project with Columbia neuroscientists Richard Axel and Larry Abbott, btw].
They use an antennae model, and the indispensable fruit fly, but it's all close enough to humans, I mean that's why we use the fruit fly in the first place. They started with some artificial neurons, of the same amount found in a fruit fly. They programmed the neurons to identify odors, and to assign valence (pleasant or unpleasant) to odors. They didn't give the neurons any structure, no information about how to talk to each other, no blueprint on how to process information. Just pre-programmed neurons, thrown into a simulated universe of chemosensation.
In minutes, and in silico, a network emerged to look just like the nose-brain of a fruit fly. All on its own, "an initially homogeneous population of neurons segregated into two populations with distinct input and output connections, resembling learned and innate pathways."
In other words, it learned how to smell. It took evolution some billions of years to get the fruit fly olfactory system just right. The artificial network did it in minutes. Extrapolations from the study abstract: "This implies that convergent evolution reflects an underlying logic rather than shared developmental principles."
-Image credit: Chris Thomasson via Fractal Forums - Expanded - 2017
*Their structure used expansion and compression layers, similar to the pyramidal-structure of the nose-brain, and the number of inter-connections was also the exact same number as in the fruit fly, and it worked with both feedforward and recurrent network models, and the networks are plastic, meaning they can learn new odor associations over time.
via Massachusetts Institute of Technology's McGovern Institute for Brain Research: Peter Y. Wang et al, Evolving the olfactory system with machine learning, Neuron (2021). DOI: 10.1016/j.neuron.2021.09.010
The book Hidden Scents talks about how olfaction is an ideal model for understanding an artificial brain, for an artificial human.
Although artificial neural networks resemble natural neural activity patterns, like those used by the visual cortex for object recognition, we still don't understand how the visual cortex, or most mammalian neural circuits, are inter-connected. This time, we see how they connect, a connectome of the olfactory cortex.
Post Post Script:
And this study should be kept alongside this other one, where a physics-based computational neuroscientist came up with a pretty simple way to mimic the olfactory cortex, via University of Pennsylvania: Gaia Tavoni et al, Cortical feedback and gating in odor discrimination and generalization, PLOS Computational Biology (2021). DOI: 10.1371/journal.pcbi.1009479