| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| public:t-720-atai:atai-22:methodologies [2022/10/20 08:37] – [Architectural Principles of a CAIM-Developed System (What CAIM Targets)] thorisson | public:t-720-atai:atai-22:methodologies [2024/10/29 00:19] (current) – [First Things First: What It a Methodology?] thorisson |
|---|
| ===== Methodology ===== | ===== Methodology ===== |
| \\ | \\ |
| ==== First Things First: What It a Methodology? ==== | ==== First Things First: What is a Methodology? ==== |
| | What it is | The methods - tools and techniques - we use to study a phenomenon. | | | What it is | The methods - tools and techniques - we use to study a phenomenon. | |
| | \\ Examples | - Comparative experiments (for the answers we want Nature to ultimately give). \\ - Telescopes (for things far away). \\ - Microscopes (for all things smaller than the human eye can see unaided). \\ - Simulations (for complex interconnected systems that are hard to untangle). | | | \\ Examples | - Comparative experiments (for the answers we want Nature to ultimately give). \\ - Telescopes (for things far away). \\ - Microscopes (for all things smaller than the human eye can see unaided). \\ - Simulations (for complex interconnected systems that are hard to untangle). | |
| | Roots | Piaget | proposed the //constructivist// view of human knowledge acquisition, which states (roughly speaking) that a cognitive agent (i.e. humans) generate their own knowledge through experience. | | | Roots | Piaget | proposed the //constructivist// view of human knowledge acquisition, which states (roughly speaking) that a cognitive agent (i.e. humans) generate their own knowledge through experience. | |
| | | von Glasersfeld | "...‘empirical teleology’ ... is based on the empirical fact that human subjects abstract ‘efficient’ causal connections from their experience and formulate them as rules which can be projected into the future." [[http://www.univie.ac.at/constructivism/EvG/papers/225.pdf|REF]] \\ CAIM was developed in tandem with this architecture/architectural blueprint. | | | | von Glasersfeld | "...‘empirical teleology’ ... is based on the empirical fact that human subjects abstract ‘efficient’ causal connections from their experience and formulate them as rules which can be projected into the future." [[http://www.univie.ac.at/constructivism/EvG/papers/225.pdf|REF]] \\ CAIM was developed in tandem with this architecture/architectural blueprint. | |
| | Architectures built using CAIM | AERA | Autocatalytic, Endogenous, Reflective Architecture [[http://cadia.ru.is/wiki/_media/public:publications:aera-rutr-scs13002.pdf|REF]] \\ Built before CAIM emerged, but based on many of the assumptions consolidated in CAIM. | | | Architectures built using CAIM | \\ AERA | Autocatalytic, Endogenous, Reflective Architecture [[http://cadia.ru.is/wiki/_media/public:publications:aera-rutr-scs13002.pdf|REF]] \\ Built before CAIM emerged, but based on many of the assumptions consolidated in CAIM. | |
| | | NARS | Non-Axiomatic Reasoning System [[https://sites.google.com/site/narswang/|REF]] \\ //“If the existing domain-specific AI techniques are seen as tools, each of which is designed to solve a special problem, then to get a general-purpose intelligent system, it is not enough to put these tools into a toolbox. What we need here is a hand. To build an integrated system that is self-consistent, it is crucial to build the system around a general and flexible core, as the hand that uses the tools [assuming] different forms and shapes.”// -- P. Wang, 2004 | | | | \\ NARS | Non-Axiomatic Reasoning System [[https://sites.google.com/site/narswang/|REF]] \\ //“If the existing domain-specific AI techniques are seen as tools, each of which is designed to solve a special problem, then to get a general-purpose intelligent system, it is not enough to put these tools into a toolbox. What we need here is a hand. To build an integrated system that is self-consistent, it is crucial to build the system around a general and flexible core, as the hand that uses the tools [assuming] different forms and shapes.”// -- P. Wang, 2004 | |
| | Limitations | As a young methodology very little hard data is available to its effectiveness. What does exist, however, is more promising than constructionist methodologies for achieving AGI. || | | Limitations | As a young methodology very little hard data is available to its effectiveness. What does exist, however, is more promising than constructionist methodologies for achieving AGI. || |
| |
| | \\ Self-Construction | It is assumed that a system must amass the vast majority of its knowledge autonomously. This is partly due to the fact that it is (practically) impossible for any human or team(s) of humans to construct by hand the knowledge needed for an AGI system, and even if this were possible it would still leave unanswered the question of how the system will acquire knowledge of truly novel things, which we consider a fundamental requirement for a system to be called an AGI system. | | | \\ Self-Construction | It is assumed that a system must amass the vast majority of its knowledge autonomously. This is partly due to the fact that it is (practically) impossible for any human or team(s) of humans to construct by hand the knowledge needed for an AGI system, and even if this were possible it would still leave unanswered the question of how the system will acquire knowledge of truly novel things, which we consider a fundamental requirement for a system to be called an AGI system. | |
| | \\ Baby Machines | To some extent an AGI capable of growing throughout its lifetime will be what may be called a "baby machine", because relative to later stages in life, such a machine will initially seem "baby like". \\ While the mechanisms constituting an autonomous learning baby machine may not be complex compared to a "fully grown" cognitive system, they are nevetheless likely to result in what will seem large in comparison to the AI systems built today, though this perceived size may stem from the complexity of the mechanisms and their interactions, rather than the sheer number of lines of code. | | | \\ Baby Machines | To some extent an AGI capable of growing throughout its lifetime will be what may be called a "baby machine", because relative to later stages in life, such a machine will initially seem "baby like". \\ While the mechanisms constituting an autonomous learning baby machine may not be complex compared to a "fully grown" cognitive system, they are nevetheless likely to result in what will seem large in comparison to the AI systems built today, though this perceived size may stem from the complexity of the mechanisms and their interactions, rather than the sheer number of lines of code. | |
| | Semiotic Opaqueness | No communication between two agents / components in a system can take place unless they share a common language, or encoding-decoding principles. Without this they are semantically opaque to each other. Without communication, no coordination can take place. | | | Semantic Transparency | No communication between two agents / components in a system can take place unless they share a common language, or encoding-decoding principles. Without this they are semantically opaque to each other. Without communication, no coordination can take place. | |
| | \\ Systems Engineering | Due to the complexity of building a large system (picture, e.g. an airplane), a clear and concise bookkeeping of each part, and which parts it interacts with, must be kept so as to ensure the holistic operation of the resulting system. In a (cognitively) growing system in a dynamic world, where the system is auto-generating models of the phenomena that it sees, each which must be tightly integrated yet easily manipulatable and clearly separable, the system must itself ensure the semiotic transparency of its constituents parts. This can only be achieved by automatic mechanisms residing in the system itself, it cannot be ensured manually by a human engineer, or even a large team of them. | | | \\ Whole-Systems \\ Systems Engineering | Retrofitting a fundamental principle unto an already-designed architecture is impossible, due to the complexity of building a large system (picture, e.g. an airplane). Examples include time, learning, pattern matching, attention (resource management). In a (cognitively) growing system in a dynamic world, where the system is auto-generating models of the phenomena that it sees, each which must be tightly integrated yet easily manipulatable and clearly separable, the system must itself ensure the semiotic transparency of its constituents parts. This can only be achieved by automatic mechanisms residing in the system itself, it cannot be ensured manually by a human engineer, or even a large team of them. | |
| | \\ Self-Modeling | To enable cognitive growth, in which the cognitive functions themselves improve with training, can only be supported by a self-modifying mechanism based on self-modeling. If there is no model of self there can be no targeted improvement of existing mechanisms. | | | \\ Self-Modeling | To enable cognitive growth, in which the cognitive functions themselves improve with training, can only be supported by a self-modifying mechanism based on self-modeling. If there is no model of self there can be no targeted improvement of existing mechanisms. | |
| | Self-Programming | The system must be able to invent, inspect, compare, integrate, and evaluate architectural structures, in part or in whole. | | | Self-Programming | The system must be able to invent, inspect, compare, integrate, and evaluate architectural structures, in part or in whole. | |
| |
| |
| ===== Example of CAIM in Action: AERA Models ===== | ===== Example of Constructivist-Inspiration in Action: AERA Models ===== |
| |
| \\ | \\ |
| |
| | \\ In a Nutshell | AERA does not only perform things it knows, it can learn //new// things. \\ And when it has learned new things it can yet again learn //more// new things. \\ And any of those new things can be //novel// things. \\ And those novel things can be //fairly different// as well as //highly similar// to what it already knows; an AERA agent can leverage this, to implement what we have called //cumulative learning//. \\ **Learning //a number of diverse novel things// requires something over and beyond what is available through the traditional learning methods: //Hypothesis generation// through //analogy//.** | | | \\ In a Nutshell | AERA does not only perform things it knows, it can learn //new// things. \\ And when it has learned new things it can yet again learn //more// new things. \\ And any of those new things can be //novel// things. \\ And those novel things can be //fairly different// as well as //highly similar// to what it already knows; an AERA agent can leverage this, to implement what we have called //cumulative learning//. \\ **Learning //a number of diverse novel things// requires something over and beyond what is available through the traditional learning methods: //Hypothesis generation// through //analogy//.** | |
| | Hypothesis Generation | To deal with new phenomena it creates //hypotheses// about it - which variables matter, how these are related, how they respond to actions, etc. \\ How these hypotheses are created: \\ 1. Based on correlations between measurements taken in the context of the phenomenon. \\ 2. How similar parts of the phenomenon are to other known phenomena. 'Similarity' is another word for "analogy". | | | \\ Hypothesis Generation | To deal with new phenomena it creates //hypotheses// about it - which variables matter, how these are related, how they respond to actions, etc. \\ How these hypotheses are created: \\ 1. Based on correlations between measurements taken in the context of the phenomenon. \\ 2. How similar parts of the phenomenon are to other known phenomena. 'Similarity' is another word for "analogy". | |
| | Analogy | Analogy is the systematic comparison of two things, where some parts of those things are ignored while others are rated on a scale as to how similar they are. | | | Analogy | Analogy is the systematic comparison of two things, where some parts of those things are ignored while others are rated on a scale as to how similar they are. | |
| | Model Creation | AERA creates models that capture the relations between variables and other models, esp. causal relations. \\ This makes AERA models very effective for \\ 1. Generating predictions. \\ 2. Creating plans. \\ 3. Explaining how 'things hang together', and \\ 4. Re-creating systems. | | | \\ Model Creation | AERA creates models that capture the relations between variables and other models, esp. causal relations. \\ This makes AERA models very effective for \\ 1. Generating predictions. \\ 2. Creating plans. \\ 3. Explaining how 'things hang together', and \\ 4. Re-creating systems. | |
| |
| \\ | \\ |
