Would someone please ban this spambot?
From: Mike Tintner Sent: Friday, August 24, 2012 2:01 PM To: AGI Subject: Re: [agi] Pattern: definition & incremental syntax Boris, Yet another definition of pattern: this really isn’t going to win any prizes for definitions – you’ve been criticised for lack of clarity, and this is a classic example. Wiki is simple enough: A pattern, from the French patron, is a type of theme of recurring events or objects, sometimes referred to as elements of a set of objects.The elements of a pattern repeat in a predictable manner However, ALL THESE PATTERN DEFINITIONS DON’T REALLY MATTER. Basically, **there is no substantive disagreement about the nature of patterns.** We ,may use different terms and definitions but we’re all talking in all our disagreements about the same things. So let’s get to your (& other AGI-ers’) main contention: “semantic concepts, .. are either generalized empirical patterns (objects & processes), or are strictly relational. There is no other way to define a concept” This is absolute nonsense – & a central issue for AGI. **THERE IS NOT ONE SINGLE CONCEPT THAT CAN BE DEFINED AS A PATTERN**. “Tree”... “box”.. “car”... “go”... “hit”... “shoot”... “pattern”... “form..” ..”shape..” “government..” “A.I.”.....*Obama*.. *love*...*sex*... *red*... *colour* None of these are patterns - or refer to patterned groups of objects/actions. Take any of these concepts and you will find that the different examples, past, present and still-to-be-realised in the future, do NOT present “matching inputs” per you, or “repeating elements” or “common elements in common positions” or any other definition or reality of patterns. SOME members of the group may fit a pattern, but a concept embraces a WHOLE group, not just odd members. The whole group is never patterned. Let’s make this v. clear and inescapable – neither you nor anyone else are going to present **one single concept** in the language that can be defined as representing a pattern/patterned objects or actions/ patterned subjects. Not one single concept. Not one example. There are probably at least a million concepts available to you – show one that represents a pattern. Boris? Ben? Jim? Prisco? (If B & B can’t put up a single patterned concept, neither has any business writing patternist manifestoes and books – and should junk them forthwith). The patternist approach represents a complete and utter failure to understand the nature of *conceptual thinking*/language – wh.; I shall discurse upon another time. The fundamental nature of all concepts is that they are, by design, *general* (“can’t be tied down to specifics”), *vague*, *open-ended*, and *multiform* – the complete opposite of patterns and logic and maths, which are *specific* (“can be tied down to specifics”), *precise*, *closed-ended*, and *uniform*. If you can’t master conceptual thought – and no one has – you can’t do AGI – and can’t survive in the real world. The real world is not patterned as a whole – in any of its scenes. Conceptual thought is the diametrical *opposite* of patterned/formulaic/algorithmic thinking. From: Boris Kazachenko Sent: Friday, August 24, 2012 5:53 PM To: AGI Subject: [agi] Pattern: definition & incremental syntax In a hopeless attempt to clear some of the confusion about patterns & concepts, here is an excerpt from my recently edited part 4: A pattern is a set of matching inputs, the same concept as fuzzy cluster in terms of unsupervised learning. In my model, match is quantified by comparison as a measure of compression, so a pattern is a compressed representation of multiple inputs. Technically, every compared input forms a pattern, but only those with an above-average compression count, - they are forwarded to higher levels for extended search. Compression is adjusted for overlap in aggregated match & miss representation: partial redundancy to previously forwarded cross-compared inputs. This adjustment increases selectivity/ sparseness of representation on a higher level. A more exclusive definition of a pattern is the recurrent match itself: a subset of each input shared across a set thereof. This is actually a higher-derivation pattern: an above-average match of a match. Just like above-average match selects an input for a higher-level search, above-average match of a match selects a common subset to a higher integration vs. differentiation level within a pattern itself. That subset also has a priority for extended search. The most basic hierarchical sub-differentiation within a pattern is by match of a binary sign for relative match, forming continuous segments of above | below average match across input queue. Selective elevation increases both predictive value & potential syntactic complexity of patterns: the number of different variables within it. Thats because comparison of each input variable adds two new variable types: relative match (m) & miss (d) relative to same-type variable of a template pattern. Both are signed, as well as aggregated across multiple comparisons within the length of a constant sign: L(m) & L(d). Relative match determines comparison vs. aggregation for individual differences, forming a queue of ds within positive L(m). New types of derivatives are also formed by comparison across different types of S-T or derived coordinates. ..... The patterns I described here are not qualitatively different from our semantic concepts, which are either generalized empirical patterns (objects & processes), or are strictly relational. There is no other way to define a concept. Given sufficient computational resources & discoverable mathematical shortcuts, search over incrementally complex syntax will discover patterns / concepts on & beyond the level of natural language. http://www.cognitivealgorithm.info/2012/01/cognitive-algorithm.html AGI | Archives | Modify Your Subscription AGI | Archives | Modify Your Subscription ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
