On 6/25/2017 5:28 PM, Edwina Taborsky wrote:
interesting outline - and I'd need to spend a lot more time on it.
I realize that 112 slides are a bit much to digest. So I deleted 93 slides to create a short version (title page + 18 slides): http://www.jfsowa.com/talks/vrshort.pdf In the short version, I addressed the distinction between perception and cognition. I wanted to emphasize two points: 1. Peirce's semiotic is still at the forefront of ongoing research in cognitive science, and it can provide the unifying framework that shows how the loosely related disciplines fit together. 2. The currently hyped "deep" neural networks address perception, which is important, but it's just the beginning of cognition.
At a quick glance, slide 41 seems to fit into the Peircean three categories with 'unsupervised learning'; 'reinforcement learning' and 'supervised learning'.
Yes. Unsupervised learning starts with raw data. Reinforcement learning reacts to some rewards or punishments. And supervised learning has a mediating supervisor that determines which responses to reward or punish. But that's one of the slides I deleted because the added explanations would raise more questions that would require more slides... In any case, vrshort.pdf has a pointer to the longer vrmind.pdf, if anyone wants to continue. John
----------------------------- PEIRCE-L subscribers: Click on "Reply List" or "Reply All" to REPLY ON PEIRCE-L to this message. PEIRCE-L posts should go to [email protected] . To UNSUBSCRIBE, send a message not to PEIRCE-L but to [email protected] with the line "UNSubscribe PEIRCE-L" in the BODY of the message. More at http://www.cspeirce.com/peirce-l/peirce-l.htm .
