Looks like a cellular automaton to me.https://twitter.com/Havenlust/status/1236426453895524353 …
-
0:08 -
Replying to @rhyolight
I thought the same. It struck me that we can construct a learning computer from this, and a lot of information processing in biological systems (plants, ecosystems) may work by similar principles.
1 reply 0 retweets 1 like -
Replying to @Plinz
This mechanism is driven by local inhibition. Local inhibition is crucial to spatial pooling in cortex. I'm drawn to HTM in the same way I was always drawn to CA for similar reasons. Nature finds simple rules that answer complex questions.
1 reply 0 retweets 2 likes -
Replying to @rhyolight
Do you think that HTM is both simple and general enough? What's missing?
1 reply 0 retweets 0 likes -
Replying to @Plinz
The SP/TM mechanisms are very low level and can provide a memory structure. There is an architecture in cortex that utilizes it for general learning. Nailing it down is hard work.
1 reply 0 retweets 1 like -
Replying to @rhyolight @Plinz
I suspect someday, when we can truly map out every neuron in the brain in real time, we will see cellular automata everywhere.
1 reply 0 retweets 0 likes -
Replying to @rhyolight
In some sense, cellular organisms are multi-level cellular automata (the topology on which the patters play out is variable and generated too). On top of the neural lattice, activation patterns may be understood as cellular automata as well. It's A New Kind of Science :)
1 reply 0 retweets 1 like -
Replying to @Plinz @rhyolight
I sometimes wonder if we are missing something obvious and simple. The answer is related to how ubiquitous learning and intelligence are in nature. How much biological intelligence are we missing because it is playing out at different (slower) timescales?
1 reply 1 retweet 3 likes
If it turns out that there are relatively simple and universal principles over which general recursive control models emerge, we should expect that intelligence is ubiquitous. If intelligence is rare, it may require a very specific architecture, and should also be brittle.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
