#braininspired — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #braininspired, aggregated by home.social.
-
English – The Conversation | Self-driving cars struggle to see at night or in fog – but imitating the human brain can make them safe by Pablo Hernández Cámara, Profesor e investigador. Departamento de Ingeniería Electrónica & Laboratorio de Procesado de Imágenes, Universitat de València, Universitat de València
AI generated summary, Read the full article for complete information.
Self‑driving cars work well in clear daylight but become almost blind in darkness, rain or fog, because current AI vision systems lack the adaptive mechanisms that human eyes use. Researchers at the University of Valencia mimicked the brain’s “divisive normalisation”—a neuronal “volume‑control” that amplifies weak signals in dark scenes and attenuates bright ones—to modify standard AI models. Tests with real‑world European driving data, night‑time images from Switzerland and virtual simulators showed that the brain‑inspired models retained accurate object detection under fog and complete darkness, outperforming unmodified AI by more than 20 %. The study suggests that improving autonomous‑vehicle safety does not require larger computers or massive datasets, but rather can be achieved by borrowing evolution‑tested strategies from human vision, making AI systems more robust, adaptable, and trustworthy in all weather conditions.
#UniversityofValencia #Selfdrivingcars #AIvision #Neuralnetwork #Humanbrain #Divisivenormalisation #Switzerland #Europeandatasets #Autonomousvehicles #Braininspired #
-
I haven't boosted the #BrainInspired podcast for far too long, but you can't miss this wonderful episode with the one and only @jaanaru.
They talk about consciousness, why current #AI does not have it (not even near), how insight is generated, and why academic research currently produces so little of it...
I just felt myself nodding along for the whole two hours...
Check it out!
-
Cool podcast episode on how we, our brain, form and use memories , 1.5hrs https://braininspired.co/podcast/206/
As audio-only and as YT video.
With transcript. So if you find the guest's Ciara Greene fast Irish difficult to follow you can read along.
#neuroscience #BrainInspired -
Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!
It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
A neuromorphic multi-scale approach for heart rate and state detection
https://doi.org/10.21203/rs.3.rs-5737326/v1
#neuromorphic #wearable #neuroai #SpikingNeuralNetwork -
Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!
It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
A neuromorphic multi-scale approach for heart rate and state detection
https://doi.org/10.21203/rs.3.rs-5737326/v1
#neuromorphic #wearable #neuroai #SpikingNeuralNetwork -
Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!
It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
A neuromorphic multi-scale approach for heart rate and state detection
https://doi.org/10.21203/rs.3.rs-5737326/v1
#neuromorphic #wearable #neuroai #SpikingNeuralNetwork -
Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!
It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
A neuromorphic multi-scale approach for heart rate and state detection
https://doi.org/10.21203/rs.3.rs-5737326/v1
#neuromorphic #wearable #neuroai #SpikingNeuralNetwork -
Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!
It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
A neuromorphic multi-scale approach for heart rate and state detection
https://doi.org/10.21203/rs.3.rs-5737326/v1
#neuromorphic #wearable #neuroai #SpikingNeuralNetwork -
New #braininspired
#MazviitaChirimuuta
#TheBrainAbstracted
#Simplification in the #History & #Philosophy of #Neuroscience
» when we try to understand something complex, like the brain, using models, and math, and analogies, for example - we should keep in mind these are all ways of simplifying and abstracting away details to give us something we actually can understand.
...
necessary to do the science and limit the interpretation we can claim from our results «
https://youtu.be/NwNHW4otoJQ
#neurobuzz -
I just listend to the #BrainInspired podcast with Andrea Martin. @andrea https://braininspired.co/podcast/169/
It was a tour de force on a variety of #linguistics and #nlp/ #LLMs topics. Wow.
-
@NicoleCRust @debivort @MolemanPeter @knutson_brain @kordinglab @dsmith @tdverstynen Right, so contextual constraints as causes just goes one important step further. The emergent properties that are hard to predict also meaningfully constrain the relationships/interactions between the individual components. Neurons are constrained by their neighbors, which are constrained by other brain areas, which are constrained by the brain as a whole, which are constrained by other people's brains, etc. These are all top-down constraints that can cause the "lower" components to behave in ways that would not be possible otherwise and would lack meaning without relation to the whole. If you define cause as efficient cause only, that's OK, and these can be labeled constraints. But I view them as equally causal.
And I'd formally model this myself but I know my limits ;)
I encourage you to check out Juarrero's book, even first 30 pages or so makes the point clear. Or listen to her on #braininspired for a summary.
-
Check out this discussion moderated by Paul Middlebrooks from #BrainInspired with yours truly & a number of actual neuroscientists (Katrin Franke, Ralf Haefner, Martin Hebart & Fred Wolf) about if & how machine learning can be used to gain insights into the brain: https://braininspired.co/podcast/177.
-
This latest episode of the #BrainInspired podcast, where Paul Middlebrooks interviews @WiringtheBrain is finger-licking good!
https://braininspired.co/podcast/175
I'm reading "Free Agents" right now, and it's amazingly well written, accessible, and gets right to the point.
https://press.princeton.edu/books/hardcover/9780691226231/free-agents
Agency is real, not doubt about it, and it's not even that mysterious.
-
Another #BrainInspired Cool Episode conversing @WiringtheBrain new book:
» what I’ve done in the book is sketch what I think is just really a framework for thinking about those things
...
that an organism could have causal power in and of itself and could could have control and could exercise choice.
...
even after having written this book, this question of choice is the one that still just niggles at me and «
https://braininspired.co/podcast/175/ -
Cool #BrainInspired Surprise:
#ContextChangesEverything comes about 25 years after her previous classic #DynamicsInAction
#AliciaJuarrero is a philosopher and has been interested in complexity since before it was cool
https://braininspired.co/podcast/174/
#complexsystems
#neurotheory
#NeuronalEnsemble
#mindbrain
#neurodon
#neuroscience
#neurobuzz
#constraints
#systemsneuroscience -
» @summerfieldlab book:
Natural General Intelligence:
How understanding the brain can help us build AImakes the case that inspiration & communication between the #CogSci & #AI is hindered by the different languages each field speaks.
But in reality, there has always been and still is a lot of overlap and convergence about ideas of computation and intelligence, and illustrates this using tons of historical and modern examples «
-
I really liked this new episode of Brain Inspired. I may be settling into familiarity with the interview style, or I might have just listened to a few episodes that gave me an incorrect impression there are frequent interruptions of guests.
The discussion of what the alpha frequency in EEG really represents was nice (it comes more than 30 minutes in). I'll have to check out Ole Jensen's work!
https://brain-inspired.castos.com/episodes/bi-160-ole-jensen-rhythms-of-cognition
-
Awaiting for listening it!
Recent triplet pods specifically inspirational to me:
BI 150
Dan Nicholson
Machines, Organisms, ProcessesBI 152
Michael L. Anderson
After Phrenology - Neural ReuseBI 155
Luiz Pessoa
The Entangled Brainps: msg that #BrainInspired listeners await them to join the #neurodon fam!
-
What's a 'memory trace'? How do we store memories? How do we recall memories?! How on earth does memory work at all!?!
Sarah Robins understands more than most, and talks about Philosophy of Memory on the Brain Inspired podcast.
#SarahRobins #Philosophy #PhilosophyOfMemory #BrainInspired #MemoryTraces