Thursday, 27 November 2008

Thinking of idealised units of link-node-link chains organised by context?

Relevant threads

- By virtue of reflexive and reflective reasoning then reflexive and reflective thinking?
- FROM SIMPLE ASSOCIATIONS TO SYSTEMATIC REASONING: A Connectionist representation of rules, variables, and dynamic bindings using temporal synchrony
- The paradigm shifts in our minds
- Handles-tags drag along thoughts from our minds
- "Use-it-or-lose-it" pruning of brain cells. An on-the-fly brain mechanism for dynamic minds?

I read in the paper by Lokendra Shastri and Venkat Ajjanagadde 'From simple associations to systematic reasoning', under the title 'Computational constraints', section 1.2

"Connectionist models (Feldman & Ballard 1982; Rumelhart & McClelland 1986) are intended to emulate the information processing characteristics of the brain — albeit at an abstract computational level — and reflect its strengths and weaknesses. Typically, a node in a connectionist network corresponds to an idealized neuron, and a link corresponds to an idealized synaptic connection.
Let us enumerate some core computational features of connectionist models: i) Nodes compute very simple functions of their inputs, ii) They can only hold limited state information — while a node may maintain a scalar ‘potential’, it cannot store and selectively manipulate bit strings. iii) Node outputs do not have sufficient resolution to encode symbolic names or pointers. iv) There is no central controller that instructs individual nodes to perform specific operations at each step of processing.

A node, in a connectionist or any other kind of network for that matter, corresponds to an idealised neuron, and a link to an idealised synaptic connection? Taking it further, a node corresponds to neural pathways connecting links, pathways which can include one idealised neuron or several idealised neurons? The main point being the passage of the signal from link-to-link? And not just any link, but a certain kind of link? A link, a synaptic connection, that lies within the context, the link-node-link path is attached to? A neurological basis of context? That links are attached by nodes, in link-node-link neural chains abiding to rules (... of context?)

Link-node-link creation, independent of length, namely the number of neurons involved. Independent also of the distance between individual links, or their place in the brain? What only matters is their placement within the contextual link-node-link chains? And one other thought that connects our brain organisation, with chaotic and fractal aspects. It is the potential inherent in such mode of brain organisation that even a remote, unused link, deeply buried, in all sense implied, can instantiate itself, unearth the attributes is attached with, and confer in the meaning of the currently active link-node-link unit.

Take the matter of idealised units, beyond a computational level, and instead talk about idealised units on the basis of context? Providing a simple mechanism for instantiating a thought, a unit of emergent thought, and multiple copies out of the same blueprint interacting, leading to complexity and the emergence of the mind?

The little red riding hood example and the steps in the inferential processing,

"The wolf will approach LRRH (to eat something you have to be near it); LRRH will scream (because a child is scared by an approaching wild animal); upon hearing the scream the wood-cutters will know that a child is in danger (because a child’s screaming suggests that it is in danger); the wood-cutters will go to the child (people want to protect children in danger and in part, this involves determining the source of the danger); the wood-cutters will try to prevent the wolf from attacking LRRH (people want to protect children); in doing so the wood-cutters may hurt the wolf (preventing an animal from attacking may involve physical force ...); so the wolf decides to wait (because an animal does not want to get hurt)."

a link-node-link path, and each link jump adds attributes that amass in the meaning conferred by the link-node-link chain, in a manner that comes out, from what the authors refer to as the “unary or even propositional fixation” problem

"This turns out to be a difficult problem for neurally motivated models. As McCarthy (1988) observed most connectionist systems suffer from the “unary or even propositional fixation” with their representational power restricted to unary predicates applied to a fixed object. Fodor and Pylyshyn (1988) have even questioned the ability of connectionist networks to embody systematicity and compositionality."

as 'unary predicates applied to a fixed object'?

Links thought off as handles or tags that involve their own specific load of attributes and properties, and drag along what is relevant to the context of the active node-link-node chain?

Though their potential surpasses their mere role in providing inferences for instantiating reasoning. By virtue of their associations with other conceived thoughts, that might even belong in other contextual units, can form context to context bridges, can drag along attributes that belong in other contexts, borrowing from context to context, passing from context to context and use that in innovating manners, the hallmark of creativity.

Wednesday, 12 November 2008

By virtue of reflexive and reflective reasoning then reflexive and reflective thinking?

Following up the threads

- Thinking (with)in and (with)out the brain.
- FROM SIMPLE ASSOCIATIONS TO SYSTEMATIC REASONING: A Connectionist representation of rules, variables, and dynamic bindings using temporal synchrony
- The minds we make overall stupid despite being generated by an underlying remarkable ability to draw inferences?
- Intuitions. Should we be afraid or trust our intuitions? Building up a case for trust.
- Neural processes beat rational thinking.
- Not recommended: frantically seeking escape from a chaotic situation, we find ourselves in.
- Is thinking an automatic process?
- Unconscious knows better ... Indulge yourself.
- Our neurons chart the space we unfold our actions in
- Mind sets and their overriding influence

This paper by Lokendra Shastri and Venkat Ajjanagadde 'From simple associations to systematic reasoning' got me going. I felt that their conclusion, arrived from a somewhat different path, matches what I have arrived using different leads. Or might be simply that I have not wholesomely (systematically) engaged in their views, despite being aired since 1992.

I felt, I have to go through, trod again the path that led me to the views, currently prevalent in my mind, but I am hesitating as I can not decide how to do that. While I am in that process, I recognise the source of my dilemma, given by the authors account of reasoning, as they differentiate it, in reflexive and reflective reasoning.

As the authors stated

"As the above examples suggest, we can draw a variety of inferences rapidly, spontaneously and without conscious effort — as though they were a reflex response of our cognitive apparatus. In view of this let us describe such reasoning as reflexive (Shastri 1990).2 Reflexive reasoning may be contrasted with reflective reasoning which requires reflection, conscious deliberation, and often an overt consideration of alternatives and weighing of possibilities. Reflective reasoning takes takes longer and often requires the use of external props such as a paper and pencil. Some examples of such reasoning are solving logic puzzles, doing cryptarithmetic, or planning a vacation."

Is the clash within me, in choosing the mode of reasoning, I want to use to deal with the notions put forward. Reflexive reasoning or reflective reasoning. Though, to my mind is quite evident that my preferred way is in favour of the reflexive reasoning than reflective reasoning, as I found it to be more productive. Thus stated, I should point out that I do not ignore the significance of reflective reasoning, though I find reflexive reasoning a more suitable way to deal with problems.

By pondering on these thoughts I realize that the case on reasoning, the authors mention, do not include what I have contemplated on the matter. The matter being, that reasoning is only a small part of the brain processes that go under the much wider umbrella concept of thinking. Surpassing the limits and extending the scope by attaching the attributes associated with reasoning, as they are revealed by their findings, to be included in the attribute repertoire of the much wider concept of thinking.

Regarding reasoning the authors mention

" reasoning underlies even the most commonplace intelligent behavior."

which they see as

"One could argue that some of the steps in the above reasoning process are pre-compiled or ‘chunked’, but it would be unreasonable to claim that this entire chain of reasoning can be construed as direct retrieval or even a single step inference!"

not just a matter of retrieving information already stored, but as

"Hence, in addition to accessing lexical items, parsing, and resolving anaphoric reference, some computation similar to the above chain of reasoning must occur when the sentence in question is processed."

computations which make it possible, as in the case of language understanding to

"... language understanding, a task that we usually perform rapidly and effortlessly, depends upon our ability to make predictions, generate explanations, and recognize speaker’s plans."

predict, explain, recognize plans in other individuals minds. And all these are done rapidly and effortlessly.

It is not just reasoning that humans can perform effortlessly, as the authors point out, but even wider aspects of thinking. Adopting the authors terminology for reasoning to this wider view of mental activity, should consider referring to thinking along the same terms as reflexive and reflective thinking.

One ill that plagued me is the use of the words-symbols for attributes and properties amassed as they develop in my mind. The notion of orphan attributes and properties springs forth. Or better, as all these attributes are amassing, mainly by virtue of their associations, converge into something, which to my mind represents the concept. The matter conceived by the amassed orphan attributes.

This thought emanating, by the authors elaboration on the individual's, designated as agent, long-term knowledge base

"... it must include, besides other things, our knowledge of naive physics and naive psychology; facts about ourselves, our family and friends; facts about history and geography; our knowledge of artifacts; sports, art, and music trivia; and our models of social and civic interactions."

naively originated thoughts and in the process, being fleshed up, demand to be acknowledged and respected. Out of the chaos in my mind converging into stable attractors, forming visible structures, entities that need to be dressed up with words to symbolize their existence, and as such to become part either as attributes or any other form along the lines mentioned by the authors

"... hierarchy that represents entities, types (categories), and the super/sub-concept relations between them ..."

entities, types, categories, super/sub-concept hierarchies. To overcome their naive origins to more informed states, towards overarching and lucid meaning. From naive roots seeking out the word, the symbol to denote the converged distinct entity.

Thinking instantiates, using up the brain reflex mechanisms, named as reflex responses of human agents cognitive apparatus, taking advantage their effortless, spontaneous remarkably efficient character, to use the speed of their processing, to arrive to new knowledge quicker. Since reflexively processing the thoughts can produce many more associations than if it was processing the thoughts reflectively.

Advancing from naive, ill-, mis-, under- informed knowledge to more inclusive empowering knowledge, broadening and deepening the long-term knowledge base, towards the empowered state of an individual.

.... not just to reason but to think too.