Epstein Secrets

. for instance, in the 19th-century philosophy of Charles Peirce IPei:341, in the writings of contempo- rary philosophers Daniel Dennett [Den91J and Douglas Hofstadter 1110179, I lo1961, in Benjamin Whorl's tj linguistic philosophy and Gregory Bateson's lam 79] systems theory of mind and nature. Bateson spoke of

urations that carry out sensorimotor and categorization tasks. The emergence of higher-level cognition from this approach seems rather unlikely. • Ben Kuipers and his colleagues INIK07, MKOS, NIKOalhave pursued an extremely innovative research program which combines qualitative reasoning and reinforcement

robot movement, may be supplied with a knob that can take on values corresponding to multiple possible movements. Following a metaphor suggested by Douglas Hofstadter MOSES learning covers both "knob twiddling" (setting the values of knobs) and "knob creation." MOSES is invoked within CogPrime in a number of way

r the various cognitively-relevant properties of the environment from looking at data about the ev- eryday world. We agree in principle, and in fact Ben Kuipers and his colleagues have done some interesting work in this direction, showing that learning algorithms can infer some basics about the structure of

nt, for instance, in the 19th-century philosophy of Charles Peirce [Pei34], in the writings of contempo- rary philosophers Daniel Dennett [Den91] and Douglas Hofstadter [Hof79, Hof96], in Benjamin Whorf’s [Who64] linguistic philosophy and Gregory Bateson’s [Bat79] systems theory of mind and nature. Bateson spoke of t

igurations that carry out sensorimotor and categorization tasks. The emergence of higher-level cognition from this approach seems rather unlikely. e Ben Kuipers and his colleagues [MK07, MIX08, MIXO09]have pursued an extremely innovative research program which combines qualitative reasoning and reinforcement

r robot movement, may be supplied with a knob that can take on values corresponding to multiple possible movements. Following a metaphor suggested by Douglas Hofstadter [Hof96], MOSES learning covers both “knob twiddling” (setting the values of knobs) and “knob creation.” MOSES is invoked within CogPrime in a number

er the various cognitively-relevant properties of the environment from looking at data about the ev- eryday world. We agree in principle, and in fact Ben Kuipers and his colleagues have done some interesting work in this direction, showing that learning algorithms can infer some basics about the structure of s