linkedin facebook twitter rss

20 Nov Identifying and Acquiring Knowledge

Key To Knowledge

One of the simplest knowledge systems is a photograph. It consists of a systematically arranged collection of pixels and its design is based almost completely on framing and focusing. Specifying knowledge software involves framing the knowledge domain and focusing on the aspects that are meaningful to users, and the constraints that affect meaning. By so saying, […]

17 Nov Environmental Awareness for AI Geeks

Selecting an Environment and Tools I plan to take a few posts in this section to focus on expert systems (Giarratano 1989), exploring the development process in greater detail. While some projects require no development, some require you to select a platform or development environment or both. There are specially designed development platforms, tools and environments that provide much of the […]

15 Nov Planning a Knowledge Project

Gantt Chart

Deliverables and the Business Case If you are a developer, a project manager, or a project sponsor of an expert system (Weiss 1984) or knowledge-based engineering project, it is very important to know early what the deliverables will be for everyone involved. Even in agile projects, where detailed requirements evolve through the course of development, […]

28 Oct Chemicals And Cognitive Performance

Lightning Brain

Outside Influences Mind-altering chemicals, stimulants, depressants and hallucinogens to name a few, affect the entire process of cognition, from receiving and processing input, through recognition and reasoning. They often even improve or impair our ability to act, affecting everything from muscle performance to language production and comprehension. Bacteria and viruses can also impact people. Things that come from outside […]

21 Oct Fuzzy Interconnectedness

Phone Brain

Fuzzy and Interconnected Techniques Section 5 suggests that the software of cognition is very fuzzy and able to operate efficiently even without having complete or totally accurate information. We said that we want to replicate that flexibility. We spoke in Section 7 about different fuzzy approaches for representing and processing information. These approaches include artificial […]

17 Oct Neural Conceptual Dependency

Representing Conceptual Graphs

Conceptual Dependency Much of this blog has been about knowledge representation: how the brain might learn and process it, how cognitive functions treat knowledge, and now, how computers may store and process it. Conceptual structures and conceptual dependency theories for computation have been useful for categorizing and representing knowledge in intuitively simple and cognitively consistent […]

14 Oct Knowledge in Non-Neural Models

Concept Graph

Non-Neural Models So far we have examined a number of models that are explicitly designed to be neuromorphic. This categorization is useful for two reasons: the apparent chaos or non-deterministic functioning of the brain is represented by these models; and neural networks explicitly use large numbers of distributed processors or neurodes that each contribute to […]

09 Oct Resolving a Paradox

Square Paradox

In time and space some things are impossible, but the pen is more powerful than reality. I can draw a world in which stairs lead in crazy, mind-bending directions, and I could probably build a structure that implemented upside-down staircases to nowhere. But I could never build the cube shown here, because it violates some […]

08 Sep Gnostic Learning Model

Hard Disk in Brain

In prior posts in this section, and periodically in other sections of my blog, I have been exploring how humans learn, and how we might replicate those processes in computer software or (less likely) hardware. The context of the learning, or knowledge acquisition, upon which I choose to focus is language learning. While knowledge acquisition is much broader, this is an […]

28 Aug Weight Control for Knowledge

Scale

Stochastic Models Data, information and knowledge may be stored in many different ways in computers. Most artificial neural models rely heavily on stochastic or probabilistic techniques for establishing the internal structure that represents the data. The generalized delta rule for adaptation is an example of this sort of technique. The generalized delta rule, developed by D.E. […]