Differences

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

--- public:t-720-atai:atai-20:self-x [2020/09/25 14:09] – [Explainability] thorisson
+++ public:t-720-atai:atai-20:self-x [2024/04/29 13:33] (current) – external edit 127.0.0.1
@@ Line 1: / Line 1: @@
 [[public:t-720-atai:atai-20:main|T-720-ATAI-2020 Main]] \\
 [[public:t-720-atai:atai-20:Lecture_Notes|Links to Lecture Notes]]
+\\
+\\
 \\
 \\
@@ Line 100: / Line 102: @@
 |  \\ When is the quality of a program evaluated?  | a) After execution, according to its actual contribution [G] \\ b) Before execution, according to its definition or historical record [I, S, P] \\ c) Both of the above [A, E, R] \\ Relevant assumption: \\  Are adaptation and prediction necessary?   |
 |  source  | [[http://alumni.media.mit.edu/~kris/ftp/JAGI-Special-Self-Progr-Editorial-ThorissonEtAl-09.pdf|Thórisson et al. 2012]]   |
-\\
-\\
 ==== Integrated Cognitive Control ====
 |  What it is  | The ability of a controller / cognitive system to steer its own structural development - architectural growth (cognitive growth). The (sub-) system responsible for meta-learning.   |
 |  Cognitive Growth  | The structural change resulting from learning in a structurally autonomous cognitive system - the target of which is self-improvement.  |
-\\
-\\
 ==== Cognitive Growth ====
@@ Line 127: / Line 127: @@
 |  What It Is  | The ability of a machine to always return the same - or similar - answer to the same input.   |
 |  Why It Is Important  | Simple machine learning algorithms are very good in this respect, delivering high reliability. Human-level AI, on the other hand, may have the same limitations as humans in this respect, i.e. not being able to give any guarantees.   |
-|  Human-Level AI  | To make human-level AI reliable is important because a human-level AI without reliability cannot be trusted, and hence would defeat most of the purpose for creating it in the first place. AERA proposes a method for this - through continuous pee-wee model generation and refinement.   |
+|  Human-Level AI  | To make human-level AI reliable is important because a human-level AI without reliability cannot be trusted, and hence would defeat most of the purpose for creating it in the first place. (AERA proposes a method for this - through continuous pee-wee model generation and refinement.)   |
+|  To Achieve Reliability  | Requires **predictability**. Predictability requires sorting out //causal relations// (without these we can never be sure what lead to what).   |
+|  Predictability is Hard to Achieve  | In a growing, developing system that is adapting and learning (3 or 4 levels of dynamics!) achieving predictability can only be achieved by **abstraction**: Going to the next level of detail (e.g. I cannot be sure //what exactly// I will eat for dinner, but I can be pretty sure that I //will// eat dinner).    |
+|  Achieving Abstraction  | Can be done through hierarchy (but it needs to be //dynamic// - i.e. tailored to its intended usage, as the circumstances call for - because the world has too complex combinatorics to store precomputed hierarchies for everything).   |
 \\