Herself’s Artificial Intelligence

This is just a small start but as smart phones get faster processors and more memory I expect to see lots of artificial intelligence coming to cell phones.

. . . Paperless data exchange between field workers and their offices is not new. But Florida startup JumpStart Wireless is bringing it to regular cell phones with software that bridges incompatibilities among handsets.

Using artificial intelligence, the Delray Beach-based company’s application fits most business software, and works with nearly every cell phone brand. Users like the Indianapolis university say it saves time and money on paperwork, data entry, labor costs and auditing . . .

My Palm Treo has a 312Mhz processor and 128 Mb of ram. That would have been cutting edge technology in the mid 1980s. Add in the internet and that it is portable and all sorts of possibilities arise.

More information:
Visual search coming to a cell phone near you
JumpStart Wireless
Workers Use Cell Phones to Submit Data
US boffins design ‘iPod supercomputer’

. . . Mehrotra taught Ann everything she knows about analyzing markets, but it’s clear who calls the shots about Legend’s $1.5 billion portfolio.

Shashi Mehrotra of Legend Advisory Corp. created Asset Allocation Neural Network, an artificial intelligence program. Ann zips through stock and bond analysis and decides how clients should move money among investment types.

When he and Ann disagree about a decision — perhaps she thinks it’s time to trim holdings in foreign markets and move the proceeds to U.S. large-cap stocks — Mehrotra has learned to let her have her way.

“Nine out of 10 times, I’m wrong, and she’s right,” he said recently from his office, as Ann sat silently nearby.

Maybe that’s because Ann doesn’t get caught in the emotional traps that snare so many investors. She doesn’t watch CNBC, and she doesn’t mind betting against the crowd.

“She doesn’t have any attitude. She doesn’t get tired,” Mehrotra said of Ann. “She’s fearless, she’s emotionless, she’s greedless.”

She’s also a computer model. Mehrotra has spent more than a decade creating and tweaking what he calls his Asset Allocation Neural Network, AANN by her initials and “Ann” in conversation . . .

More information:
When it’s time to invest, Gardens firm turns to Ann

Natural language processing allows people to interact with computers and robots in a more natural way. There are five major areas in NLP: Speech recognition, Language processing, Language understanding, Language generation, Speed synthesis.

Speech recognition consists of breaking down speech into words. Most modern systems require a pause between words so the computer knows where one word ends and another begins.

Language processing is breaking down of words it is then parsed using grammar rules and a lexicon. A lexicon is a list of words to be understood by the computer and attributes for those words( noun/verb/etc ). The grammar is a formal description of the language. It might have rules explaining how sentences may be formed example Subject->NounPhrase->Verb or NounPhrase->VerbPhrase etc. Sometimes you have parsers that break a sentence down into parts and a parse tree. Other times you have a recognizer which parses the sentence and determines if it is valid with the grammar and lexicon supplied.

Understanding is mapping the processed language onto a representation that the computer can handle.

Language generation is the formation of an answer by the machine. Usually these are predefined phrases.

Speech synthesis is the verbal expression of the language generated and is also usually predefined phrases.

Language is difficult to parse structure can be as simple as two word sentences or complex lengthy sentences. By using a limited grammar and lexicon this can be simplified.

Language can also be ambiguous words can some times be nouns or verbs ( a run – to run ; a program – to program ). This can create multiple possible parse trees from a single statement.

Metaphors are not well translated by machines.

Parsers can be top down, bottom up, or finite state machines. Top down parsers start with sentences and work down to words. When every word has been classified it is complete. Bottom up parsing starts with words applying rules to parse them into verb and noun phrases until a sentence can be fit into a sentence rule. Finite state machines work from the bottom up. Finite state machines identify words and work through a graph like structure to form the sentence.

NLP is used in speech interfaces, text processing, language translation and information retrieval. It is an important tool in the war against spam.

More information:
Stanford School of Engineering, Natural Language Processing Online Course
Simon: Open source speech to text software
Natural Language Processing Blog
Getting Started with OpenNLP ( Natural Language Processing )
Has voice recognition finally come of age?

See also:
Darpa builds speech translator
Neural net learing vowels

This week teams of robots from all over the world are taking part in Robocup 2007 – the robotic football World Cup.

This year the event is taking place at Georgia Tech university in the US for the biggest ever demonstration of robotic footballing prowess.

While they might not have the guile or pace of Wayne Rooney just yet, scorelines that stretched into double figures proves that these robo-soccer stars certainly have a grasp of the game’s fundamentals.

The groups ranged from the ‘Humanoid League’ right through to robots so small they can only be seen with a microscope in the inaugural ‘Nano-Cup’.

More information:
RoboCup Official Site
World Cup for robots kicks off

University scientists are providing the artificial intelligence systems for the wheels on the company’s prototype eco-friendly electric super-car. The wheels use microcomputers to perform 4000 calculations per second and ‘talk’ to each other. The wheels use AI to think and learn as the car is being driven, making calculations and adjustments according to travelling speed and road conditions.

It is the first time artificial intelligence has replaced fundamental mechanics within a motor vehicle and will mean tighter control, a smoother ride and a safer drive, yet the driver remains in control of the car….

More information:
University of Portsmouth scientists reinvent the wheel