linkedin facebook twitter rss

29 Dec Unhuman Expertise

Expert System Architecture with Common Sense

Artificial Intelligence has suffered from a persistent scale problem: up to now, many techniques have been shown to work well and reliably in narrowly defined domains, but outside the domains of their expertise, they fall apart very quickly. No techniques of which I am aware, have exhibited common sense in the way we expect humans […]

23 Dec Visual Knowledge Dimensions

Statistical Analysis

Visualizing knowledge in graphs and charts empowers decision makers by giving them actionable knowledge in understandable format. To make this most effective, the labels on the graph must provide clearly defined context cues that make it easy to interpret. Converging data strategies using Big Data (Hadoop, NoSQL, Cassandra, MapReduce…) can change the way we access content […]

10 Dec Measuring Knowledge

Measuring Knowledge

Sometimes you need to know about your knowledge. When you’re in the middle of trying to build a system that knows stuff, you may ask, how much does the system know after this training or learning cycle as a percent of the total knowable amount? When we test students in their learning cycles, we use a […]

25 Aug Determinacy in Neural Connections

Neural Net

For many years, researchers thought that it was wrong to assume that there was a cell or set of cells in the brain that stored the memory of Grandma’s face. Though the comparison with computer memory was appealing, it was thought to be too simplistic and incorrect. Now, more researchers in different academic disciplines are assuming […]

28 Jul Patterns in the Mind

Learning Head

As we look for suitable solution designs for representing the knowledge and processes we humans use to communicate, we realize that we have no idea what knowledge in the brain looks like. Further, we only have relatively vague ideas about the processes that occur in the brain as we produce and comprehend words, phrases and sentences. […]

15 Jul From Perception and Learning to Logic

Software of Thought

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 […]

10 Jun Survival of the Fittest Knowledge

Genetic Search

Genetic Algorithms in Search I think we can safely assume that intelligent applications, including accurate language interpreters and translators, will possess large amounts of knowledge to be processed and searched. Genetic algorithms are great for searching for obscure data in massive search spaces. The mechanism for association in computers can be defined as searching, just as humans describe their […]

07 Jun Finding a Tree in the Forest

Forest Trees

Complex Search Finding the information you need can be a problem, particularly when you have to look through tons (or terabytes) of data. I recall when geocaching first became popular. The idea that a technology could create a model for an entertaining activity that connects people in unusual ways is quite diverting. Will it still be popular […]

19 May Deixis and Context

Written Language

Deixis, is a common type of ambiguity that is mediated at the level of context. When deixis occurs in written language, you can normally resolve questions about the identity of the person(s) referenced in the ‘he’, ‘she’ or ‘they’ pronoun. In speaking, you sometimes have to ask the person who said it. 3-DG places context in […]