By and large, after many, many years of dreams during sleep, I have come to the conclusion that they are probably just artifacts from neural management functions (sorting, retrieval, merging and storing, garbage collection, etc.), and have no major significance in and of themselves.
Artificial neural networks connect disparate bits of information that could be plausibly connected, which we view as a hallucination.
While we’re dreaming, our organic neural network connects disparate bits of information which could be plausibly connected, but are not necessary or helpful, so it flushes them out via dreams, as sleeping hallucinations.
Let’s bring back into the limelight Jurgen Schmidhuber’s ~2009 take on compression as the root of a lot that goes on in learning and its impact/causality on beauty, novelty, boringness/interestingness, and action selection.
“Driven by compression progress: A simple principle explains essential aspects of subjective beauty, novelty, surprise, interestingness, attention, curiosity, creativity, art, science, music, jokes” by Schmidhuber 2008. https://arxiv.org/pdf/0812.4360
Can anyone help with understanding how to best do #modelselection in the context of #neuralnetworks ? I'm trying to understand how to reduce #bias due to the selection of a particular test set.
The development of neural networks to create artificial intelligence in computers was originally inspired by how biological systems work. These "neuromorphic" networks, however, run on hardware that looks nothing like a biological brain, which limits performance.
...movement predators, all interacted in brain development.
Your source continues:
"Or perhaps #consciousness emerges in any sufficiently complex network?"
IMO, as there already have been inexplicable occurrences and humanity has been experimenting with #NeuralNetworks capable of learning; I think the likelihood of this assumption being true is quite high.
"If, on the other hand, they are conscious, we should surely..."
An interesting article here by @mimsical and I would recommend reading it.
I think it is a reasonable take on how, essentially, the regulatory landscape will look in the US and perhaps elsewhere.
That said, I have some notes.
Not so much on the article itself... but on my favorite punching bag, the #NHTSA.
For those that do not know, the NHTSA is the unserious, disinterested and effectively theoretical regulator in the US for vehicle and roadway safety. 🧵
"It’s increasingly looking like this may be one of the most hilariously inappropriate applications of AI that we’ve seen yet." I am riveted by the extensive documentation of how ChatGPT-powered Bing is now completely unhinged. @simon has chronicled it beautifully here: https://simonwillison.net/2023/Feb/15/bing/
If we look at the international situation today: #ClimateCrisis, wars, one small parties of humanity living relatively well in a #PostColonial world order, it would take any #GAI I've read about in #SciFi but a split second to determine what's the root of the problem: #humanity.
And then, no...
Alas, my knowledge of all the exciting fields involved is only rudimentary, however I am certain that by having created #NeuralNetworks capable if learning, providing more stimuli than any biological system ever experienced its...
Researchers grow bio-inspired polymer brains for artificial neural networks (phys.org)
The development of neural networks to create artificial intelligence in computers was originally inspired by how biological systems work. These "neuromorphic" networks, however, run on hardware that looks nothing like a biological brain, which limits performance.