User Tools

Site Tools


public:t_720_atai:atai-19:lecture_notes_methodologies

Differences

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

Link to this comparison view

public:t_720_atai:atai-19:lecture_notes_methodologies [2019/09/11 16:41]
thorisson [Lecture Notes, W4: AI Methodologies]
public:t_720_atai:atai-19:lecture_notes_methodologies [2019/09/17 10:27] (current)
thorisson [Constructivist AI Methodology (CAIM)]
Line 210: Line 210:
 ====Constructivist AI Methodology (CAIM) ==== ====Constructivist AI Methodology (CAIM) ====
 |  What it is  | A term for labeling a methodology for AGI based on two main assumptions: (1) The way knowledge is acquired by systems with general intelligence requires the automatic integration, management, and revision of data in a way that //infuses meaning// into information structures, and (2) constructionist approaches do not sufficiently address this, and other issues of key importance for systems with high levels of general intelligence and existential autonomy.   || |  What it is  | A term for labeling a methodology for AGI based on two main assumptions: (1) The way knowledge is acquired by systems with general intelligence requires the automatic integration, management, and revision of data in a way that //infuses meaning// into information structures, and (2) constructionist approaches do not sufficiently address this, and other issues of key importance for systems with high levels of general intelligence and existential autonomy.   ||
 +|  \\ Why We Need It  | Most AI methodology to date has automatically inherited all standard software methodological principles. This approach assumes that software architectures are hand-coded and that (the majority of) the system's knowledge and skills is hand-fed to it. In sharp contrast, CAIM assumes that the system acquires the vast majority of its knowledge on its own (except for a small seed) and manages its own GROWTH on its own. Also, it may change its own architecture over time, due to experience and learning.     ||
 |  Why it's important  | It is the first and only attempt so far at explicitly proposing an alternative to current methodologies and prevailing paradigm, used throughout AI and computer science.   || |  Why it's important  | It is the first and only attempt so far at explicitly proposing an alternative to current methodologies and prevailing paradigm, used throughout AI and computer science.   ||
 |  What it's good for  | Replacing present methods in AI, by and large, as these will not suffice for addressing the full scope of the phenomenon of intelligence, as seen in nature.   || |  What it's good for  | Replacing present methods in AI, by and large, as these will not suffice for addressing the full scope of the phenomenon of intelligence, as seen in nature.   ||
Line 261: Line 262:
  
 ==== Some Key Requirements For a Constructivist AGI Architecture ==== ==== Some Key Requirements For a Constructivist AGI Architecture ====
-|  Tight Integration  | A general-purpose system must tightly and finely coordinate a host of skills, including their acquisition, transitions between skills at runtime, how to combine two or more skills, and transfer of learning between them over time at many levels of temporal and topical detail.    | +|  \\ Tight Integration  | A general-purpose system must tightly and finely coordinate a host of skills, including their acquisition, transitions between skills at runtime, how to combine two or more skills, and transfer of learning between them over time at many levels of temporal and topical detail.    | 
-|  Holistic Integration  | The architecture of an AGI cannot be developed in a way where each of the key requirements (see above) is addressed in isolation, or semi-isolation, due to the resulting system's whole-part semiotic opaqueness: When a system learns new things, to see whether it has learned it before, and use it to improve its understanding, it must relate the new knowledge to its old knowledge, something we call **//integration//**. The same mechanisms needed for integration also enable transfer knowledge; it is these same mechanisms that (in humans) are responsible for what is known as "negative transfer of training", where a priorly learned skill makes it //harder// to learn something new (this happens in humans when the new task is //almost// like the old one, but deviates on some points. The more critical these points are in mastering the skill, the worse the negative transfer of training.    |+|  \\ Holistic Integration  | The architecture of an AGI cannot be developed in a way where each of the key requirements (see above) is addressed in isolation, or semi-isolation, due to the resulting system's whole-part semiotic opaqueness: When a system learns new things, to see whether it has learned it before, and use it to improve its understanding, it must relate the new knowledge to its old knowledge, something we call **//integration//**. The same mechanisms needed for integration also enable transfer knowledge; it is these same mechanisms that (in humans) are responsible for what is known as "negative transfer of training", where a priorly learned skill makes it //harder// to learn something new (this happens in humans when the new task is //almost// like the old one, but deviates on some points. The more critical these points are in mastering the skill, the worse the negative transfer of training.    |
 |  Transversal Functions  | The system must have pan-architectural characteristics that enable it to operate consistently as a whole, to be highly adaptive (yet robust) in its own operation across the board, including metacognitive abilities. Some functions likely to be needed to achieve this include attention, learning, analogy-making capabilities, and self-inspection.   | |  Transversal Functions  | The system must have pan-architectural characteristics that enable it to operate consistently as a whole, to be highly adaptive (yet robust) in its own operation across the board, including metacognitive abilities. Some functions likely to be needed to achieve this include attention, learning, analogy-making capabilities, and self-inspection.   |
 |  \\ \\ Time  | Ignoring (general) temporal constraints is not an option if we want AGI. Move over Turing! Time is a semantic property, and the system must be able to understand – and be able to //learn to understand// – time as a real-world phenomenon in relation to its own skills and architectural operation. Time is everywhere, and is different from other resources in that there is a global clock which cannot, for many task-environments, be turned backwards. Energy must also be addressed, but may not be as fundamentally detrimental to ignore as time while we are in the early stages of exploring methods for developing auto-catalytic knowledge acquisition and cognitive growth mechanisms.  | |  \\ \\ Time  | Ignoring (general) temporal constraints is not an option if we want AGI. Move over Turing! Time is a semantic property, and the system must be able to understand – and be able to //learn to understand// – time as a real-world phenomenon in relation to its own skills and architectural operation. Time is everywhere, and is different from other resources in that there is a global clock which cannot, for many task-environments, be turned backwards. Energy must also be addressed, but may not be as fundamentally detrimental to ignore as time while we are in the early stages of exploring methods for developing auto-catalytic knowledge acquisition and cognitive growth mechanisms.  |
-|  \\ Large Aarchitecture  | An architecture that is considerably more complex than systems being built in most AI labs today is likely unavoidable. In a complex architecture the issue of concurrency of processes must be addressed, a problem that has not yet been sufficiently resolved in present software and hardware. This scaling problem cannot be addressed by the usual “we’ll wait for Moore’s law to catch up” because the issue does not primarily revolve around //speed of execution// but rather around the //nature of the architectural principles of the system and their runtime operation//.   |+|  \\ Architecture Based on New Principles  | An architecture that is considerably more complex than systems being built in most AI labs today is likely unavoidable. In a complex architecture the issue of concurrency of processes must be addressed, a problem that has not yet been sufficiently resolved in present software and hardware. This scaling problem cannot be addressed by the usual “we’ll wait for Moore’s law to catch up” because the issue does not primarily revolve around //speed of execution// but rather around the //nature of the architectural principles of the system and their runtime operation//.   |
 |  Predictable Robustness   | The system must have a robustness in light of all kinds of task-environment and embodiment perturbations, otherwise no reliable plans can be made, and thus no reliable execution of tasks can ever be reached, no matter how powerful the learning capacity.   | |  Predictable Robustness   | The system must have a robustness in light of all kinds of task-environment and embodiment perturbations, otherwise no reliable plans can be made, and thus no reliable execution of tasks can ever be reached, no matter how powerful the learning capacity.   |
 |  \\ Graceful Degradation  | Part of the robustness requirement is that the system be constructed in a way as to minimize potential for catastrophic failure. A programmer can forget to delimit a command in a compiled program and the whole application crashes; this kind of brittleness is not an option for cognitive systems that operate in stochastic environments, where perturbations can come in any form at any time.   | |  \\ Graceful Degradation  | Part of the robustness requirement is that the system be constructed in a way as to minimize potential for catastrophic failure. A programmer can forget to delimit a command in a compiled program and the whole application crashes; this kind of brittleness is not an option for cognitive systems that operate in stochastic environments, where perturbations can come in any form at any time.   |
/var/www/ailab/WWW/wiki/data/attic/public/t_720_atai/atai-19/lecture_notes_methodologies.1568220091.txt.gz · Last modified: 2019/09/11 16:41 by thorisson