Unlimited Quote Collections
Organize your favorite quotes without limits. Create themed collections for every occasion with Premium.
[E]verything that we're going to do is some approximation of Solomonoff Induction. ...[O]ur concepts cannot really refer to facts in the world out th… - Joscha Bach
" "[E]verything that we're going to do is some approximation of Solomonoff Induction. ...[O]ur concepts cannot really refer to facts in the world out there. We do not get the truth by referring to stuff out there in the world. We get meaning by suitably encoding the patterns in our systemic interface.
English
Collect this quote
About Joscha Bach
, also known as “the wizard of consciousness”(born 1973 in Weimar, Germany) is a cognitive scientist focusing on cognitive architectures, models of mental representation, emotion, motivation and sociality. Achievements include research in novel data compression algorithm using concurrent entropy models; development of microPsi cognitive architecture for modeling emotion, motivation, mental representation. In 2000, Bach graduated with a diploma in Computer Science from Berlin, followed by a Doctor of Philosophy at Osnabrück University, Germany, in 2006. Before joining , he worked as a visiting researcher at the and the Harvard Program for Evolutionary Dynamics. Fact finding reports by the and found that Bach’s research was supported with more than $150,000 by the Foundation.
Related quotes. More quotes will automatically load as you scroll down, or you can use the load more buttons.
Additional quotes by Joscha Bach
[T]here also seems to be a particular kind of ground truth, [e.g.,] you are confronted with the enormity of something existing at all. ...It's stunning when you realize something exists, rather than nothing. ...[T]his seems to be true. There is an absolute truth in the fact that something seems to be happening.
[C]ausal models can be weakly deterministic, basically associative models, which tell you if this state [S<sub>1</sub>] happens, it is quite probable that this one [S<sub>2</sub>] comes afterwards. Or you can get to a strongly determined model... one which tells you, if you are in this state [S<sub>1</sub>], and this condition [c<sub>1</sub>] is met, you're going to go exactly in this state [S<sub>2</sub>]. If this state is not met, or a different condition [c<sub>2</sub>] is met, you go into this state [S<sub>3</sub>]. And this is what we call an algorithm. Now you're in the domain of computation.
PREMIUM FEATURE
Advanced Search Filters
Filter search results by source, date, and more with our premium search tools.
Symbolic reasoning falls short not only in modeling low level behaviors but is also difficult to ground into real world interactions and to scale upon dynamic environments... This has lead many... to abandon symbolic systems... and... focus on parallel distributed, entirely sub-symbolic approaches... well suited for many learning and control tasks, but difficult to apply [in] areas such as reasoning and language.
Loading...