Thursday, April 18, 2013

infoTabby is back!

infoTabby is back and is being retooled. She will no longer be tied to a single library, but will be able to search a variety of physical and digital collections. My colleague and good friend Michele McNeal is working on this with me, and we hope to have the new search capabilities coded in the next few weeks. In the meantime, please say "Hello" to our catbot. Some of you have asked about the chatscript version, Emma2. Right now, that project should be finished by June 1, and will be available as open source. Thanks for your patience!

Thursday, March 21, 2013

infoTabby will be back soon.

I had to take some time away from this project, as you can see. My job at Lakeland Community College has  been keeping me busy, and last November I started working with a developer on an AI project unrelated to libraries. Besides being very rewarding, the latter convinced me to begin a more formal and comprehensive training in programming.

There have been some useful developments to the AIML markup language in the last few months, notably the <set> tag. The AIML version of infoTabby may be rewritten to include these if time allows. ChatScript has also continued to develop and can now boast of a number of commercially successful apps. At this point, the ChatScript version of our library bot will take priority; I just need to find a quiet weekend to finish the scripting.

Please check back again soon.

Sunday, July 1, 2012

Google's Neural Network teaches itself to recognize...cats

If you follow AI, you've already heard the news. Google's simulation of a neural network taught itself how to identify cats after a week of watching YouTube videos. It had never been given even a single image labeled as a cat; it was never told what a cat was. It taught itself from unlabeled images.

Besides image recognition, this research will have applications in speech recognition and natural language processing. (As in Google's own version of SIRI).

As soon as the neural network believes that it is itself a cat, the feline conquest of the internet and AI will be complete!

Here's the story:

Monday, May 14, 2012

My new ChatScript bot

I've been working on a ChatScript version of infoTabby, tentatively named "Emma2." I started this bot less than a month ago, on April 19th. The results have been so encouraging that the new bot will be available as a separate Google Code project. The majority of library information has been coded; the table containing OhioLINK database information is the largest unfinished piece and should be completed by the end of this week. A link to the new Google code project will be posted on this blog.

Thursday, April 26, 2012

Version 1-6b available

infoTabby version 1-6b is now available. Generic library information has been made easier to locate and customize using "find and replace" in your text editor.

Monday, April 16, 2012

Library directory coming soon

A set of AIML files to replace "contact.aiml" will be available soon. The new files will be constructed as a database - you just fill in the names, titles, phone numbers, and so on. Further work and improvements are being made to the material type attribute files. Please check the Google Code repository for the latest files. A new download incorporating these improvements should be available by the end of April.

Thursday, April 12, 2012

Computers in Libraries 2012, Chatbots 3.2

Spring is the time for presentations and travel. Last month infoTabby and her human friends presented at Computers in Libraries 2012 and at Chatbots 3.2. Both went well. My apologies for not releasing v1-5b as promised; I decided to skip it entirely and move to v1-6 which gathers the majority of the info you need to edit into one file and allows you to set material type attributes. It's good to be home and back to work!