Thanks for that, Eric. It's clarifying. --- Frank C. Wimberly 140 Calle Ojo Feliz, Santa Fe, NM 87505
505 670-9918 Santa Fe, NM On Wed, Nov 11, 2020, 9:43 AM David Eric Smith <[email protected]> wrote: > Yes, it seems that the kind of reporting that would be natural for expert > systems does not have a good reason to map to deep neural nets. To the > extent that I refer to the right architectures as “expert systems”, I think > of them as having a knowledge structure dictated by the architect. Reading > out parts of it that are used short of the conclusions as an “explanation” > integrates naturally into the architecture as it is. > > For neural nets, the part that one engineers is a combinatorial parameter > space that is both very large and very high-dimensional. The learning loop > guide the dynamics into some region in that space, but in what sense “being > in that region” is a representation of regularities in the inputs is for > the architect to discover, but largely not to have designed. > > Thus it seems that “reporting” entails the invention of a representation > that is matched both to the particular state of the neural net, which it > may not have a way to survey, and to the comprehension standards of people, > to which it has no way to be coupled at all. That kind of invention seems > like a meta-operation of the process on its own internal state, and a > higher-order function. > > I wonder if there is some crowd-sourcing protocol, by which the AI could > propose representations of its internal state, and a distributed pool of > users through feedback to it (kind of like Ken Stanley’s picbreeder) could > represent criteria for human comprehension, by which the meta-operation > would be implemented as just one more layer of reinforcement learning. > Probably end up with 70 million Fox viewers, and 70 million more Elvis > fans, standing in for human comprehension. > > But I don’t work in this area, and will stop now. > > Eric > > > > On Nov 11, 2020, at 11:21 AM, Frank Wimberly <[email protected]> wrote: > > I used to teach a course called "AI and expert systems" for management > students at Carnegie Mellon. I remember that Mycin, a diagnosis system for > infectious diseases and one of the most famous expert systems, had some > explanation capability. According to Wikipedia, "At the end, it [Mycin] > provided a list of possible culprit bacteria ranked from high to low based > on the probability of each diagnosis, its confidence > <https://en.m.wikipedia.org/wiki/Confidence_interval> in each diagnosis' > probability, the reasoning behind each diagnosis..." > > But after publishing a few papers in the area I left that field. I > assumed, mistakenly it seems, that later AI implementations did the same. > Too bad. > > By the way, I realize, that AI systems can't assess non-respondent bias in > the way it was done in Project Talent but perhaps there is some "machine > readable" way to do it. > > --- > Frank C. Wimberly > 140 Calle Ojo Feliz, > Santa Fe, NM 87505 > > 505 670-9918 > Santa Fe, NM > > On Wed, Nov 11, 2020, 9:05 AM David Eric Smith <[email protected]> > wrote: > >> >> >> On Nov 11, 2020, at 8:54 AM, Frank Wimberly <[email protected]> wrote: >> >> Don't some AI systems include subsystems for explaining their reasoning? >> >> >> I don’t know how common that is, Frank. The few people I know who are >> active and skilled deep-learning practitioners have told me (if I have >> understood) that it is rare and limited. I spent some time looking at the >> zero-shot language translation, as something I wanted to convene at SFI, >> with the AI goal of unpacking what was the “universal language” internal >> representation, and with the linguistics goal of using it in cognate >> classification and historical reconstruction. Never could get a call-back >> from any of the google people. But I didn’t think at the time that >> zero-shot had been unpacked. >> >> Probably some on this list know much more about the state of play. >> >> Eric >> >> >> Happy Veterans Day, >> >> Frank >> >> --- >> Frank C. Wimberly >> 140 Calle Ojo Feliz, >> Santa Fe, NM 87505 >> >> 505 670-9918 >> Santa Fe, NM >> >> On Wed, Nov 11, 2020, 3:25 AM David Eric Smith <[email protected]> >> wrote: >> >>> Friam poll: >>> >>> How soon until classical telephone polling is just gone? >>> https://www.nytimes.com/2020/11/10/upshot/polls-what-went-wrong.html >>> >>> If, as boasted, facebook knows when their users are pregnant before the >>> users know, they know who someone supports and whether that person is >>> likely to vote. >>> >>> At this stage, trying to get accurate statistics from cold calls on the >>> phone seems as quixotic as trying to infer something from the people who >>> read books. But if there’s anything we can count on, it is that the number >>> of people who don’t leave an internet fingerprint is too small to have any >>> political impact at all. >>> >>> How much effort they put into getting reliable calibrations will depend >>> on what ways they see to monetize it, but the diversity of cash-outs should >>> be nearly inexhaustible, for years to come. >>> >>> So one more thing goes into what is both a black box and a private >>> rather than public box. It will take over after the first few times it >>> produces much more reliable results, but since we won’t know what it is >>> based on — AIs don’t explain themselves — we will have no ability to >>> extrapolate out of sample. >>> >>> Eric >>> >>> >>> - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . >>> FRIAM Applied Complexity Group listserv >>> Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam >>> <https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fbit.ly%2fvirtualfriam&c=E,1,MIlehtrxasGxzXCBAG-Wuptie4wVpHZCod2H9fKLPnfs1yGvGgHBDARSwVq4VdCdtzq4Dow-kWiVv4jc9hIVdl8zyYLkXNCJ81WlPwU_cCV-Wj_FaKxE&typo=1> >>> un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com >>> <https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fredfish.com%2fmailman%2flistinfo%2ffriam_redfish.com&c=E,1,eEyTIKAnKXKW32Kg5QjvWagEgRoLZi2PtyoqSEHHUN3kS4q1_QFqepVMevdBzSM8Z9F4aZohLrRrIwqCA-ExUAfBhUBVHO7gf4xaB87f6I6MuI4i&typo=1> >>> archives: http://friam.471366.n2.nabble.com/ >>> FRIAM-COMIC http://friam-comic.blogspot.com/ >>> <https://linkprotect.cudasvc.com/url?a=http%3a%2f%2ffriam-comic.blogspot.com%2f&c=E,1,owZjlS1njud5BssZPtYtW4jYIrQySTobJWmn1LQwCyeJUf-KLCb4RIvTldGJmHVC8OL-2OunE-nqJmBcsyFM7sBJTgDRQlvwtgQpNHs3-mBAwQlugck,&typo=1> >>> >> - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . >> FRIAM Applied Complexity Group listserv >> Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam >> <https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fbit.ly%2fvirtualfriam&c=E,1,oqHFT1YdV0k75pKzx4YTF1iw_fTQ3iaPASzr-UyzEBQ9snxyN9TmgQOObG89c4hRDu0e22Rlo4Ua40Cy7mZIzFf1SCuw5JNkQYjfxrb5tGKG&typo=1> >> un/subscribe >> https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fredfish.com%2fmailman%2flistinfo%2ffriam_redfish.com&c=E,1,ZhFECaCEstC6R1KARgPxbu9IEAqI9wjTi65WxBGjDM4gwbxMCgeSOBQ2EKWK35vV6tuhdQlPpQ3q0AmGgUXMwPCscl0M5mPqvGm002E2VyScyzizkyplPu9NMaOH&typo=1 >> archives: http://friam.471366.n2.nabble.com/ >> FRIAM-COMIC >> https://linkprotect.cudasvc.com/url?a=http%3a%2f%2ffriam-comic.blogspot.com%2f&c=E,1,bcNwVv6Xg-iYdul8iBL7SSR37PBueIDjkSji3dd3y4G3o_reGRlxBEs9K8ZfZPNKeOYrtHreLpQMofHuId25yG_iN3xq5W7MgsWxOvjO&typo=1 >> >> >> - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . >> FRIAM Applied Complexity Group listserv >> Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam >> <https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fbit.ly%2fvirtualfriam&c=E,1,NoYGq6JtoxCm1xKczIKhU3YLSYqufMlPmIaDtf39TAcVMqkJCuhfJkMbfVlEpdYRFc1cD0EgP-sLVuI3zPxvBvDWh61DF3U9lI4YNqReg0i97EFnaQ,,&typo=1> >> un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com >> <https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fredfish.com%2fmailman%2flistinfo%2ffriam_redfish.com&c=E,1,iVIpbUAf1oxjjTBO9As2ReYhdIQm9v3GqeiCU6m3Z2Fo2VpBrvSH9ywZYDaQ2GuKEufkvEbsyIw6AyNeSMWEeOwSlhGnMsLm_KBlxorQsNlck8JoYLOE&typo=1> >> archives: http://friam.471366.n2.nabble.com/ >> FRIAM-COMIC http://friam-comic.blogspot.com/ >> <https://linkprotect.cudasvc.com/url?a=http%3a%2f%2ffriam-comic.blogspot.com%2f&c=E,1,ZgiI8AhBAKEz7-zoY4fne03DZafBG3HaN3bcefzRb345LdKATHx-u7cbScxyxflCPclhZKFYRgY85o-dUS2uc6Ltqj_LW1P72voPVrzW2g,,&typo=1> >> > - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . > FRIAM Applied Complexity Group listserv > Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam > un/subscribe > https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fredfish.com%2fmailman%2flistinfo%2ffriam_redfish.com&c=E,1,bWeUaJgfO8pAEvOoQ13EihOr5iHDAYpKEDbuVrrfH0tlm3YhEW0d3eC5694-3x7idkZniXSayxxaTRdW16u4_tX9cEEJFQRWctiHKSTz&typo=1 > archives: http://friam.471366.n2.nabble.com/ > FRIAM-COMIC > https://linkprotect.cudasvc.com/url?a=http%3a%2f%2ffriam-comic.blogspot.com%2f&c=E,1,OMiJ_4epUCa9FpA_LGrMSEzzBK2n-IaWeW3BeK9rkdJvD3QTGdmiPTj0T-oTTgv_r0ePB9dqJJa-mkFBHiMJtyjSGEcyQezaGiQkJddPwGD7GejfRYo,&typo=1 > > > - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . > FRIAM Applied Complexity Group listserv > Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam > un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com > archives: http://friam.471366.n2.nabble.com/ > FRIAM-COMIC http://friam-comic.blogspot.com/ >
- .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. . FRIAM Applied Complexity Group listserv Zoom Fridays 9:30a-12p Mtn GMT-6 bit.ly/virtualfriam un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com archives: http://friam.471366.n2.nabble.com/ FRIAM-COMIC http://friam-comic.blogspot.com/
