Herself’s Artificial Intelligence

Human Computer Interfaces
Game Theory
Probabilistic Graphical Models
Computer Science 101
Software as a Service
Machine Learning
Natural Language Processing
Cryptography
Design and Analysis of Algorithms I
and
Lean Launchpad
Technology Entrepreneurship

I can’t recommend these classes enough. I’ve taken the iPhone Development, Intro to Artificial Intelligence, Intro to Databases, and Machine Learning classes.

It’s my thought that the future of education will not be 4 year degrees on site, but life long learning at home.

If you need to brush up on some math first try Khan Academy, Wolfram Math World.

Stanford is offering free online classes in Machine Learning and Introduction to Artificial Intelligence

I’ve taken their iPhone programming class and it was fantastic. I’m going to take the AI class to brush up on things and the Machine Learning to learn some new things.

Classes begin Oct 10 and run through mid Dec 2011.

Malware is in the eye of the beholder

Computer scientists predict that a new generation of malware will mine social networks for people’s private patterns of behaviour

It’s not hard top find frightening examples of malware which steals personal information, sometimes for the purpose of making it public and at other times for profit. Details such as names, addresses and emails are hugely valuable for companies wanting to market their wares.

But there is another class of information associated with networks that is potentially much more valuable: the pattern of links between individuals and their behaviour in the network–how often they email or call each other, how information spreads between them and so on.

Why is this more valuable? An email address associated with an individual who is at the hub of a vibrant social network is clearly more valuable to a marketing company than an email address at the edge of the network. Patterns of contact can also reveal how people are linked, whether in a relationship for example, whether they are students or executives or whether they prefer celebrity gossip to tech news.

This information would allow a determined attacker to build a remarkably detailed picture of the lifestyle of any individual, a picture that would be far more useful than the basic demographic information that marketeers use today which consists of little more than sex, age and social grouping.

We’ll almost certainly have to deal with this one sooner or later. source

Stealing Reality

It’s not just the malware, it’s also your future employer:

However, the pre-crime concept is coming very soon to the world of Human Resources (HR) and employee management.

A Santa Barbara, Calif., startup called Social Intelligence data-mines the social networks to help companies decide if they really want to hire you.

While background checks, which mainly look for a criminal record, and even credit checks have become more common, Social Intelligence is the first company that I’m aware of that systematically trolls social networks for evidence of bad character.

Using automation software that slogs through Facebook, Twitter, Flickr, YouTube, LinkedIn, blogs, and “thousands of other sources,” the company develops a report on the “real you” — not the carefully crafted you in your resume. The service is called Social Intelligence Hiring. The company promises a 48-hour turn-around. source

Social Intelligence

New FOIA Documents Reveal DHS Social Media Monitoring During Obama Inauguration

The Emerging Web of Social Machines

If you are looking for an overview on datamining to detect fraud this paper is a good start.

A Comprehensive Survey of Data Mining-based Fraud Detection Research
Authors: Clifton Phua, Vincent Lee, Kate Smith, Ross Gayler
(Submitted on 30 Sep 2010)

Abstract: This survey paper categorises, compares, and summarises from almost all published technical and review articles in automated fraud detection within the last 10 years. It defines the professional fraudster, formalises the main types and subtypes of known fraud, and presents the nature of data evidence collected within affected industries. Within the business context of mining the data to achieve higher cost savings, this research presents methods and techniques together with their problems. Compared to all related reviews on fraud detection, this survey covers much more technical articles and is the only one, to the best of our knowledge, which proposes alternative data and solutions from related domains. source

paper ( pdf )

More information
Data mining
RapidMiner open source data mining software

Sparse distributed memory first appeared in 1998 as a model of long term memory in humans. The main idea is that distances between concepts in our brains can be represented as distances between points in a high dimension world. Since distances between points are far apart in many dimensions, the distance between concepts is large. The large distance between concepts means I only have to come closer to it than another idea for a match to be made.

For example if I give each letter of the alphabet its own dimension then map it by position in a word then ‘aeple’ is closer to ‘apple’ than ‘ample’ and I can guess that the correct word for the mistyped word. Or a four legged creature that is tall and is spotted is closer to a giraffe than a short legged spotted leopard.

This type of storage of data means you can store far fewer examples you need to match allowing you to store more information in a much smaller memory footprint.

All input is represented in binary form in sparse distributed memory. The algorithm works by calculating the ‘Hamming distance’ between data input and existing examples in memory.

Books:
Reinforcement Learning: An Introduction (pdf download )

More information:
Sparse Distributed Memory
Kevin Kelly ‘Out of Control’ Chapter 2
Sparse Distributed Memory and Related Models Chapter 3 (pdf)

Papers:
Kanerva’s Sparse Distributed Memory An associative memory algorithm well suited to the connection machine. (pdf) ( exellent starting point )
Kanerva’s Sparse Distributed Memory, Multiple Hamming Thresholds ( pdf )