| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| public:t-713-mers:mers-26:concepts_terms [2026/08/19 09:22] – [Correlation, Knowledge, Causation] thorisson | public:t-713-mers:mers-26:concepts_terms [2026/08/22 14:08] (current) – [Correlation, Knowledge, Causation] thorisson |
|---|
| | Correlation | Some factors/variables co-vary when changes in one variable are related with changes in the other, negative or positive. | | | Correlation | Some factors/variables co-vary when changes in one variable are related with changes in the other, negative or positive. | |
| | Correlation: Powerful source of information | Any variables in the world can be measured for correlation (i.e. to see if they are correlated). Only two variables are needed (independent and dependent) for doing correlation studies. | | | Correlation: Powerful source of information | Any variables in the world can be measured for correlation (i.e. to see if they are correlated). Only two variables are needed (independent and dependent) for doing correlation studies. | |
| | Main operating principle behind correlation | There is no causation without correlation. \\ BUT: It is not guaranteed to be measurable. | | | Main operating principle of correlation | \\ There is no causation without correlation. \\ BUT: It is not guaranteed to be measurable (at a particular time using particular means). | |
| | Correlation: Pitfall | Correlation does not imply causation between the variables measured! \\ BUT: ALL correlation that is NOT a coincidence has a cause. | | | Correlation: Pitfall | Correlation does not imply causation between the variables measured! \\ BUT: ALL correlation that is NOT a coincidence has a cause. | |
| | Modeling Correlation | A model that makes use of observed correlation between A and B is only good for prediction, not for manipulation; to be useful for manipulation (goal-directed behavior and planning) it must include the causal direction of the relationship between A and B. | | | Modeling Correlation | A model that makes use of observed correlation between A and B is only good for prediction, not for manipulation; to be useful for manipulation (goal-directed behavior and planning) it must include the causal direction of the relationship between A and B. | |
| | Science vs. Engineering | In science we look for the model; \\ in engineering we mold the world to behave like our model. \\ \\ // Example for science: // \\ [phenomenon] // We see something interesting and call it "**intelligence**". // \\ [model] // We come up with theories for how it works. // \\ [empirical research] // We test the models through systematic creation and evaluation of hypotheses. // \\ [create new models] // We revise the theory. // \\ \\ // Example for engineering:// \\ [model] // We have a theory of intelligence. // \\ [engineering] // We want to build an intelligent system. // \\ [implementation] // We use the theory as a blueprint. // \\ [requirements and theory] // We make sure it behaves to its specifications. // | | | Science vs. Engineering | In science we look for the model; \\ in engineering we mold the world to behave like our model. \\ \\ // Example for science: // \\ [phenomenon] // We see something interesting and call it "**intelligence**". // \\ [model] // We come up with theories for how it works. // \\ [empirical research] // We test the models through systematic creation and evaluation of hypotheses. // \\ [create new models] // We revise the theory. // \\ \\ // Example for engineering:// \\ [model] // We have a theory of intelligence. // \\ [engineering] // We want to build an intelligent system. // \\ [implementation] // We use the theory as a blueprint. // \\ [requirements and theory] // We make sure it behaves to its specifications. // | |
| | Why AI is special | Most research fields rely primarily on either the scientific research approach or the engineering approach. \\ //**AI is special in that it is committed to doing both.**// \\ (Although it does not always operate accordingly.) \\ AI is also the only field of science explicitly committed to the phenomenon of intelligence. | | | Why AI is special | Most research fields rely primarily on either the scientific research approach or the engineering approach. \\ //**AI is special in that it is committed to doing both.**// \\ (Although it does not always operate accordingly.) \\ AI is also the only field of science explicitly committed to the phenomenon of intelligence. | |
| | \\ Science + Math | We strive to make scientific theories (models of the world) mathematical because of the //compactness, precision,// and //specificity// this can give us. However, it is not guaranteed solely through the use of math because //a model must detail how it maps to the thing it is a model of//. If this is not done properly the math provides //no benefits//. \\ Mapping a model to its reference: A good scientist does it properly; a bad scientist does it sloppily; the wannabe ignores it happily. \\ Bottom line: Being mathematical is //no guarantee// for good science - it is neither necessary nor sufficient. | | | \\ Science + Math | We strive to make scientific theories (models of the world) mathematical because of the //compactness, precision,// and //specificity// this can give us. However, it is not guaranteed solely through the use of math because //a model must detail how it maps to the thing it is a model of//. If this is not done properly the math provides //no benefits//. \\ Mapping a model to its reference: A good scientist does it properly; a bad scientist does it sloppily; the wannabe ignores it obliviously. \\ Bottom line: Being mathematical is //no guarantee// for good science - it is neither necessary nor sufficient. | |
| | Science + Engineering + Math: The Holy Trinity | The three fields so defined support each other: Building better scientific models helps us engineer better; engineering better helps us build new tools for doing science better. Both are bootstrapped by philosophy and clarified through math. | | | Science + Engineering + Math: The Holy Trinity | The three fields so defined support each other: Building better scientific models helps us engineer better; engineering better helps us build new tools for doing science better. Both are bootstrapped by philosophy and clarified through math. | |
| | \\ The universe: Nothing is given | How do we know that the sun will come up tomorrow? What evidence do we have? Can we prove it mathematically that the sun will come up tomorrow? \\ The only thing we know for sure is that we can perceive things in the world and that "I am here now". (This principle is most famously captured by Rene Descartes who wrote "I doubt, therefore I think, therefore I am".) \\ But since that perception is provided/generated by the same universe that we want to claim "exists" through those senses, using those grey cells, we cannot possibly know **for sure** what that really is, and hence whether it can be trusted. \\ Therefore, the universe is (and cannot be anything but) **non-axiomatic** to us. | | | \\ The universe: Nothing is given | How do we know that the sun will come up tomorrow? What evidence do we have? Can we prove it mathematically that the sun will come up tomorrow? \\ The only thing we know for sure is that we can perceive things in the world and that "I am here now". (This principle is most famously captured by Rene Descartes who wrote "I doubt, therefore I think, therefore I am".) \\ But since that perception is provided/generated by the same universe that we want to claim "exists" through those senses, using those grey cells, we cannot possibly know **for sure** what that really is, and hence whether it can be trusted. \\ Therefore, the universe is (and cannot be anything but) **non-axiomatic** to us. | |
