In our earliest uses of neural methods we actually worked with some brain scientists. And they were quick to point out that neural methods, though inspired by the brain, were nothing like them. So our thoughts of biomimicry were dangerous. But it seems this idea has changed some, but in a glance at this non technical piece, there is still much we do not know. But is the brain a reasonable place to start for general AI?
Artificial neural networks are more similar to the brain than they get credit for By Ben Dickson in BDTechtalks
This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence.
Consider the animal in the following image. If you recognize it, a quick series of neuron activations in your brain will link its image to its name and other information you know about it (habitat, size, diet, lifespan, etc…). But if like me, you’ve never seen this animal before, your mind is now racing through your repertoire of animal species, comparing tails, ears, paws, noses, snouts, and everything else to determine which bucket this odd creature belongs to. Your biological neural network is reprocessing your past experience to deal with a novel situation.
Our brains, honed through millions of years of evolution, are very efficient processing machines, sorting out the ton of information we receive through our sensory inputs, associating known items with their respective categories. ... "
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment