Epstein Secrets

From: an behalf of Ben Goertzel =MIMI Sent: Monday, September 7, 2015 1:16 AM To: Jeffrey E. Subject: Re: I think that "learning language like a baby" is a fantastic and impo

» complex structures. The winning approach would then not be able to » work on another language for which there was no large annotated » corpus (no Penn Treebank analogue, etc.). » It seems that challenges are easier to formulate for engineering » breakthroughs than science breakthroughs... » Here is one id

ail to [email protected], > and destroy this communication and all copies thereof, including all > attachments. copyright -all rights reserved Ben Goertzel, PhD http://goertzel.org "The reasonable man adapts himself to the world: the unreasonable one persists in trying to adapt the world to himself. T

quite complex structures. The winning approach would then not be able to work on another language for which there was no large annotated corpus (no Penn Treebank analogue, etc.). It seems that challenges are easier to formulate for engineering breakthroughs than science breakthroughs... Here is one idea, off

ail to [email protected], > and destroy this communication and all copies thereof, including all > attachments. copyright -all rights reserved Ben Goertzel, PhD http://goertzel.org "The reasonable man adapts himself to the world: the unreasonable one persists in trying to adapt the world to himself. T

quite complex structures. The winning approach would then not be able to work on another language for which there was no large annotated corpus (no Penn Treebank analogue, etc.). It seems that challenges are easier to formulate for engineering breakthroughs than science breakthroughs... Here is one idea, off

ept of coherence. or sense making modules.. babys learn la=guage. many of them . figure out how the baby does it. On Sun, Sep 6, =015 at 8:16 PM, Ben Goertzel > wrote: Hi, I agree w/ Joscha's caution about discrimination tasks: They can be often be solved rather well, but in devious ways, by statistical

e=br> complex structures. The winning approach would then not be able=to work on another language for which there was no large annotated corpus (no Penn Treebank analogue, etc.). It seems that challenges are easier to formulate for engineering breakthroughs than science breakthroughs... Here is one idea, off

of coherence. or sense making modules.. babys > learn language. many of them . figure out how the baby does it. > On Sun, Sep 6, 2015 at 8:16 PM, Ben Goertzel avrote: » Hi, » I agree w/ Joscha's caution about discrimination tasks: They can be » often be solved rather well, but in devious ways, by statist

» complex structures. The winning approach would then not be able to » work on another language for which there was no large annotated » corpus (no Penn Treebank analogue, etc.). » It seems that challenges are easier to formulate for engineering » breakthroughs than science breakthroughs... » Here is one id