# Center for Analysis and Design of Intelligent Agents

### Site Tools

public:t-720-atai:atai-16:lecture_notes_f-6_29.01.2016

# Differences

This shows you the differences between two versions of the page.

public:t-720-atai:atai-16:lecture_notes_f-6_29.01.2016 [2017/12/01 14:01]
thorisson [Important Concepts for AGI]
public:t-720-atai:atai-16:lecture_notes_f-6_29.01.2016 [2017/12/01 14:03] (current)
thorisson [Important Concepts for AGI]
Line 18: Line 18:
|  Understanding  | The ability of an Agent to achieve Goals with respect to a phenomenon <m>Phi</m>, referring to a Goal state <m>G = S subset V</m>. \\ An agent's <m>A</m> //level of understanding// of a phenomenon <m>Phi</m> is the size of the set <m>G</m> of dynamically assigned goals \\ <m>{G_i(phi subset Phi) | {forall G_i:} G_i <> G_{i+1}}</m> \\ with respect to phenomenon <m>Phi</m> which <m>A</m> can achieve.  \\ Understanding is crucial but has been neglected in AI and AGI; Modern AI systems do not understand; "intelligence" as the concept is typically used does not need to -- and is not intended to -- imply understanding.  | |  Understanding  | The ability of an Agent to achieve Goals with respect to a phenomenon <m>Phi</m>, referring to a Goal state <m>G = S subset V</m>. \\ An agent's <m>A</m> //level of understanding// of a phenomenon <m>Phi</m> is the size of the set <m>G</m> of dynamically assigned goals \\ <m>{G_i(phi subset Phi) | {forall G_i:} G_i <> G_{i+1}}</m> \\ with respect to phenomenon <m>Phi</m> which <m>A</m> can achieve.  \\ Understanding is crucial but has been neglected in AI and AGI; Modern AI systems do not understand; "intelligence" as the concept is typically used does not need to -- and is not intended to -- imply understanding.  |
|  Explanation  | When performed by an Agent, the ability to transform knowledge about X from a formulation primarily (or only) good for execution with respect to X to a formulation good for being communicated (typically involving some form of linearization, incremental introduction of concepts and issues, in light of an intended receiving Agent with a particular a-priori knowledge).   | |  Explanation  | When performed by an Agent, the ability to transform knowledge about X from a formulation primarily (or only) good for execution with respect to X to a formulation good for being communicated (typically involving some form of linearization, incremental introduction of concepts and issues, in light of an intended receiving Agent with a particular a-priori knowledge).   |
-|  Learning   | Acquisition of information in a form that enables more successful completion of tasks. We call information in such a form "knowledge" or "practical knowledge". (There is also the concept of "impractical knowledge", which sometimes people feel must be the case of "useless trivia" whose only usage seems to be to wow others with, but in fact that is not impractical since it can be used in practice to wow others.)   |+|  Learning   | Acquisition of information in a form that enables more successful completion of tasks. We call information in such a form "knowledge" or "practical knowledge". (There is also the concept of "impractical knowledge", which sometimes people feel must be the case of "useless trivia" that seems to be useless for anything, but can in fact turn out to be useful at any point, as for instance using such trivia to wow others with one's knowledge of trivia.)   |
|  Life-long learning   | Incremental acquisition of knowledge throughout a (non-trivially long) lifetime.  | |  Life-long learning   | Incremental acquisition of knowledge throughout a (non-trivially long) lifetime.  |
|  Transfer learning   | The ability to transfer what has been learned in one task to another.  | |  Transfer learning   | The ability to transfer what has been learned in one task to another.  |