Joscha Bach

"How does... representation by simulation work? ...If you are a brain and you want to understand sound, you have to model it. ...Neurons do not want to do 20 Khz. Thats way too fast for them. They like something like 20 Hz. So... you need to make a [which] measures the amount of energy at different frequencies. ...This ...in our ears ...transforms energy of sound at different frequency intervals into energy measurements... This is something that the brain can model. ...[A] neurosimulator tries to recreate these patterns. If it can predict the next input from the cochlea, then it understands the sound."

"Mathematics is the kingdom of specification and computation is the kingdom of implementation. Its very important to understand this difference."

"[I]f you look at the progression of AI models, it... went the opposite direction. ...AI started with linguistic protocols, which were expressed in formal grammars, and then it got to concept spaces, and now its about to address percepts. ...At some point in the near future its going to get better at mental simulations and at some point after that well get to attention directed and motivationally connected systems that make sense of the world, that are in some sense able to address meaning. This is the hardware that we have..."

"Computation is different. Computation can exist. It starts with an initial state, and then you have a transition function. You do the work. You apply the transition function [and] you get into the next state. Computation is always finite."

"All our access to mathematics... is because we do computation. We can understand mathematics because our brain can compute some part of mathematics, very very little of it and to a very constrained complexity, but enough so we can map some of the infinite complexity and noncomputability of mathematics into computational patterns which we can explore."

"With this vector space you can do amazing things, [e.g.,] if you take the vector from king to queen, its pretty much the same vector as between man and woman. ...[B]ecause [these concept spaces are] really a high dimension manifold, we can do interesting things like machine translation without understanding what it means, that is, without doing any proper mental representation that predicts the world. ...[T]his is [a] type of mental representation that is somewhat incomplete, but it captures the landscape that we share in a culture."

"[C]omputation is about doing the work... executing a transition function."

"[T]o encode a brain genetically, based on the hardware that we are using, we need something like at least 500 kilobytes of code... actually... its going to be a little more, I guess. It sounds like surprisingly little... but in terms of scientific theories this is a lot. ...The universe, according to the core theory of quantum mechanics... its like half a page of code... to generate the universe. ...[I]f you want to understand evolution, its like a paragraph... a couple lines, really, to understand an evolutionary process. ...[T]heres lots ...of details that you get afterwards, because this process itself doesnt define what all the animals are going to look like. In a similar way, the code of the universe doesnt tell you what this planet is going to look like and you... are going to look like. Its just defining the rule book."

"Computational systems are machines that can be described apriori and systematically, and implemented on every substrate that elicits the causal properties that are necessary to capture the respective states and transition functions."

"[W]hile dynamical systems often cannot be effectively computed on a finite state machine (such as a von Neumann computer), they can often be efficiently approximated."

"Artificial Intelligence was the attempt of thinkers like Marvin Minsky, John McCarthy and others to treat the mind as a computational system, and thereby open its study to experimental exploration by building computational machines that would attempt to replicate the functionality of minds."

"[O]ur best bet is not just to have a single classification with filtering. ...[I]nstead... take the low level of input and get a whole universe of features that is interrelated. ...[W]e have different levels of determinations. At the lowest level we have percepts. At a slightly higher level we have simulations, and on an even higher level we have a concept landscape."