Tag Archives: neural network
15 Jul From Perception and Learning to Logic
Perception and Learning I am not a cognitive scientist, so all I have said in this section is based on the work of others. On the other hand, I have probably spent more time seriously studying cognition than most computer geeks, and I have tried to form my perspectives around the best of our knowledge. The […]
21 May Modeling After a Fashion
Perennial Image Problems Artificial Intelligence has an image problem. Yes, there are cybernetic characters like R2D2, C3P0 and Commander Data whom we love, but some products built using AI techniques have the dubious reputation of being useful but not entirely dependable. Think of songs sung about Sirius Cybernetics Teleporter products (see lyrics below). It is possible that […]
08 May Three-Dimensional Model of Language
Topographical maps of concepts in a text provide useful views of language. Fortuna et al in Semantic Knowledge Management (pp. 155-169) describe how three-dimensional topic maps can both give meaningful insights into clusters of related content, such as news stories or published papers. I have frequently stressed the importance of concept associations in the brain, in cognitive […]
06 May Impulse Waves in Layers
Layered Model Just as the brain has areas with three to six distinct layers, a typical artificial neural systems (ANS) also has several layers. The example at right shows a network with three layers that illustrate a neural network‘s distributed architecture. The uniform circles connected by lines are symbolic of the state of an ANS at […]
05 May Learning from Errors
If at first you don’t succeed, try – try again. Humans are pretty good at learning from our mistakes. In fact, some suggest that whatever doesn’t kill you makes you stronger. Today I’d like to riff on that theme a bit, and talk about ways in which machines can implement learning from errors. Error Minimization […]
26 Apr Continuity of Learning
Production and Comprehension We know that comprehension and language production occur in different areas of the brain and occupy opposite ends of the continuum in the communicative model. The relative independence of the production and comprehension centers suggests one of three possibilities: Syntactic and lexical data are replicated in both the production and comprehension centers of […]
20 Mar Thresholds in Fuzzy Logic
At what point does temperature change from cold to hot? Tell a person (or a computer) that the beach will be closed if the water is too cold, and their interpretation may differ from yours. This statement is subjective, as are many of the values applied to the thermometer at right. But if you tell […]
14 Mar That’s so Random!
Random Probability Theory Some things are difficult to predict, and some are nearly impossible to predict. The further a thing gets from predictable, the more nearly it approaches randomness. It may seem silly to try to define chaos or randomness or anything that spends its entire existence trying to defy definition, but some of us […]
04 Mar Gnosticism, Mysticism and Hard Knowledge
Neural Network science describes oft rejected explicit knowledge in neurons as “gnostic cells” or “gramma cells” suggesting one neuron knows about gramma. Not all scientists agree with associationist theories that explain learning in the context of things that pre-exist in memory. In fact, an entire school of thought flatly rejects explicit representations that form the core […]
27 Feb Chomsky, Locke and Aristotle on Learning Language
Inherited Abilities In systems design, there is a growing trend to “hard code” less into the system and leave more to be configured by the person or organization that is using the software. The growth of Rules and Workflow Engines that can be managed by non-technical users is prime evidence of this trend. And yet, the complex instruction […]