Scientists have modeled a neural network to display schizophrenic-like language abnormalities by decreasing the information resilience function, essentially telling the network not to forget as much of what it’s taught.
From KurzweilAI:
“The researchers taught a series of simple stories to a neural network programmed to learn and answer questions about narratives, though with an imperfect memory. When they decreased the program’s ability to forget, it started giving answers resembling those given by humans with schizophrenia.
The answers contained dissociated sentences, digressions, and delusions—at one point the computer claimed responsibility for a terrorist bombing. Answers also typically included incoherent jumbles of elements from the various stories it had been taught.”
I don’t think I can even begin to emphasize how much I long for that source code. A robot programmed just like me! \<3 Oh, and, speaking of adorable robot-type-entities, thanks to William for reading me that news article.
Excuse my incessant xkcd references.
So, now for the serious stuff. I scanned another book today: Linguistic Fuzzy Logic Methods in Social Sciences by Badredine Arfi. Linguistic fuzzy logic is used for all sorts of awesome things, including programming neural networks. This book includes applications to the Prisoner’s Dilemma in Game Theory, and Skocpol’s Theory of Revolution!
Linguistic Fuzzy Logic Methods in Social Sciences (click for .pdfs)
Forewards, Prefaces, and ToC.pdf
Chapter 1 - Linguistic Fuzzy-Logic and Computing with Words.pdf
Chapter 2 - Elements of Linguistic Fuzzy-Logic and Framework.pdf
Chapter 3 - Linguistic Fuzzy-Logic Decision-Making Process.pdf
Chapter 4 - Linguistic Fuzzy-Logic 2x2 Games.pdf
Chapter 5 - Linguistic Fuzzy-Logic Social Game.pdf
Chapter 6 - Linguistic Fuzzy-Logic and Causality.pdf
Chapter 7 - Linguistic Fuzzy-Logic Data Analysis.pdf
[
]: http://www.patternsinthevoid.net/blog/wp-content/uploads/2011/05/lisp.jpg