# Center for Analysis and Design of Intelligent Agents

### Site Tools

public:t-720-atai:atai-21:ai_architectures

# Differences

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

public:t-720-atai:atai-21:ai_architectures [2021/11/05 13:40]
thorisson [Refresher: Inferred GMI Architectural Features]
public:t-720-atai:atai-21:ai_architectures [2021/11/05 13:45] (current)
thorisson [Features of AERA]
Line 83: Line 83:
\\ \\
====Features of NARS==== ====Features of NARS====
-|  Predictable Robustness in Novel Circumstances  | Yes    | NARS is explicitly designed to operate and learn novel things in novel circumstances. It is the only architecture (besides AERA) that is directly based on, and specifically designed to, an **assumption of insufficient knowledge and resources** (AIKR).    | +|  Predictable Robustness in Novel Circumstances  | \\ Yes    | NARS is explicitly designed to operate and learn novel things in novel circumstances. It is the only architecture (besides AERA) that is directly based on, and specifically designed to, an **assumption of insufficient knowledge and resources** (AIKR).    |
-|  Graceful Degradation  | Yes | While the knowledge representation of NARS is not organized around safe, predictable, or trustworthy operation, NARS can do reflection, so NARS could learn to get better about evaluating its own performance over time, which means it would be increasingly knowledgeable about its failure modes, making it increasingly more likley to fail gracefully.   |+|  Graceful Degradation  | \\ Yes | While the knowledge representation of NARS is not specifically aimed at achieving safe, predictable, or trustworthy operation, NARS can do reflection, so NARS could learn to get better about evaluating its own performance over time, which means it would be increasingly knowledgeable about its failure modes, making it increasingly more likley to fail gracefully.   |
|  \\ Transversal Functions  | \\ Yes | //Transversal Handling of Time.// Time is handled in a very general and relative manner, like any other reasoning. \\ //Transversal Learning.// Learning is a central design target of NARS. While knowledge in NARS is not explicitly model-based, its knowledge is symbolic and NARSese statements can be thought of as micro-models; reasoning is a fundamental (some would say the only) principle of its operation. \\ //Transversal Analogies.// Yes \\ //Transversal Self-Inspection.// Yes. Via reasoning. \\ //Transversal Skill Integration.// Yes. Via reasoning.    |  |  \\ Transversal Functions  | \\ Yes | //Transversal Handling of Time.// Time is handled in a very general and relative manner, like any other reasoning. \\ //Transversal Learning.// Learning is a central design target of NARS. While knowledge in NARS is not explicitly model-based, its knowledge is symbolic and NARSese statements can be thought of as micro-models; reasoning is a fundamental (some would say the only) principle of its operation. \\ //Transversal Analogies.// Yes \\ //Transversal Self-Inspection.// Yes. Via reasoning. \\ //Transversal Skill Integration.// Yes. Via reasoning.    |
|  \\ Symbolic?  | \\ CHECK  | One of the main features of NARS is deep symbol orientation.    | |  \\ Symbolic?  | \\ CHECK  | One of the main features of NARS is deep symbol orientation.    |
Line 106: Line 106:
====Features of AERA==== ====Features of AERA====
|  Predictable Robustness in Novel Circumstances  | \\ Yes    | \\ Since AERA's learning is goal driven, its target operational environment are (semi-)novel circumstances.    | |  Predictable Robustness in Novel Circumstances  | \\ Yes    | \\ Since AERA's learning is goal driven, its target operational environment are (semi-)novel circumstances.    |
-|  Graceful Degradation  |    |  |+|  Graceful Degradation  | Yes    | Knowledge representation in AERA is based around causal relations, which are essential for mapping out "how the world works". Because AERA's knowledge processing is organized around goals, with increased knowledge AERA will get closer and closer to "perfect operation" (i.e. meeting its top-level drives/goals, for which each instance was created). Furthermore, AERA can do reflection, so it gets better at evaluating its own performance over time, meaning it makes (causal) models of its own failure modes, increasing its chances of graceful degradation.   |
|  \\ Transversal Functions  | \\ Yes | //Transversal Handling of Time.// Time is transversal. \\ //Transversal Learning.// Yes. Learning can happen at the smallest level as well as the largest, but generally learning proceeds in small increments. Model-based learning is built in; ampliative (mixed) reasoning is present. \\ //Transversal Analogies.// Yes, but remains to be developed further.  \\ //Transversal Self-Inspection.// Yes. AERA can inspect a large part of its internal operations (but not everything). \\ //Transversal Skill Integration.// Yes. This follows naturally from the fact that all models are sharable between anything and everything that AERA learns and does.    |  |  \\ Transversal Functions  | \\ Yes | //Transversal Handling of Time.// Time is transversal. \\ //Transversal Learning.// Yes. Learning can happen at the smallest level as well as the largest, but generally learning proceeds in small increments. Model-based learning is built in; ampliative (mixed) reasoning is present. \\ //Transversal Analogies.// Yes, but remains to be developed further.  \\ //Transversal Self-Inspection.// Yes. AERA can inspect a large part of its internal operations (but not everything). \\ //Transversal Skill Integration.// Yes. This follows naturally from the fact that all models are sharable between anything and everything that AERA learns and does.    |
|  \\ Symbolic?  | \\ CHECK  | One of the main features of AERA is that its knowledge is declarable by being symbol-oriented. AERA can learn language in the same way it learns anything else (i.e. goal-directed, pragmatic). AERA has been implemented to handle 20k models, but so far the most complex demonstration used only approx 1400 models.    | |  \\ Symbolic?  | \\ CHECK  | One of the main features of AERA is that its knowledge is declarable by being symbol-oriented. AERA can learn language in the same way it learns anything else (i.e. goal-directed, pragmatic). AERA has been implemented to handle 20k models, but so far the most complex demonstration used only approx 1400 models.    |