linkedin facebook twitter rss

16 Jun Genetic Cross-Pollination

Pollination

Cross Pollination Many approaches exist for simulating intelligent behavior on computers. In the past, the most popular approach was to focus on developing a technique and applying it to a problem. Most basic research has focused on single paradigms and their properties. Sometimes, however, in domains where multiple approaches to problem solving are possible, some […]

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 […]

09 Jun In Search of Depth and Breadth

Mountains in Turkey

Depth-First Search Search is one of many functions needed in intelligent systems. Web search in systems like Google, Bing, Yahoo and Alta Vista use complex algorithms to help you find the information you want based on words. Words are patterns of letters strung together in a unique way. Searching is a kind of pattern matching. […]

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 […]

07 Apr A Good Excuse for Heuristic Logic

Cogs in the Engine

Dichotomous logic is useful for reasoning about form or the way things are. Function, or cause and effect, however, is fuzzier because observation may not be enough to exclude other processes that lead to the same result. Heuristic logic applies to function instead of form, prescribing actions based facts. Heuristics often operate at a relatively […]

28 Dec [McMillan 2012]

04 Aug Context of Knowing, Thinking and Believing

Understanding Intent

There may be an incontrovertible thing out there called “truth.” But it seems quite elusive to me. In Japanese it is very polite to append just about any declarative sentence, any assertion of knowledge with “to omoimasu” (と思います) meaning I think. By being less committal, we save the other people in the conversation from embarrassment because their […]

17 Mar Intro to Cybernetic Models

Are you my Motherboard? From Eliza to Watson, Jeeves, Siri and Alfred, people have been naming their computers. Some systems are named after their inventors – like Wolfram Alpha and its siblings. Who is JARVIS? Just Another Rather Very Intelligent System? These attempts have, in their own little ways, touched our lives. But we are still waiting on the cusp of an innovation that will […]

13 Aug MIPUS the Robot Assistant

MIPUS Graphical Study Aid I’d like to introduce you to a friend of mine: His name is MIPUS. The main intent of the Understanding Context blog is to investigate mechanical models of cognition. What do robots have to do with language understanding (my main focus), you may ask. As you can see in the illustration, […]

30 Jun Gamification – The Future

Rewards

Ain’t no Passin’ Thing… Were you one of the brilliant prognosticators that said that the mouse (pointing device) was a fad and would never catch on, or that iPads wouldn’t catch on, or that the world would max out at, say, five computers? Some may scoff at the value of gamification of computer software – but they must […]