Free voice mail helps the homeless

This is one of the cooler charity projects I’ve seen. It’s a project that allows homeless shelters and food kitchens to give free voicemail boxes to homeless people. It’s great to see people who’ve actually looked at the problems of the homeless and come up with a solution that addresses a real problem that faces homeless people who are trying to get back on their feet. How can you get a job, when you don’t have a telephone number to put on the application?

This also points out the importance of providing basic infrastructure to the economically disadvantaged. I often hear these arguments like “why are we giving [insert your favorite hi-tech item here] to poor people, when what they really need is food!” Sure they need food, but maybe the reason they’re hungry is that they don’t access to the infrastructure necessary to feed themselves. A smart analysis might yield items that are actually more important than food itself. “Teach a man to fish…” and all that. Cool.

Posted in Misc. 1 Comment »

Forum for AI: Jeffrey Siskind

FAI is presenting this talk Friday:

Stochastic Spatio-Temporal Grammars for Images and Video
Jeffrey Mark Siskind
School of Electrical and Computer Engineering, Purdue University
Friday September 3, 2004 3pm (coffee at 2:30)
ACES 2.302Probabilistic Context-Free Grammars (PCFGs) induce distributions over strings. Strings can be viewed as observations that are maps from indices to terminals. The domains of such maps are totally ordered and the terminals are discrete. We extend PCFGs to induce densities over observations with unordered domains and continuous-valued terminals. We call our extension Spatial Random Tree Grammars (SRTGs). While SRTGs are context sensitive, the inside-outside algorithm can be extended to support exact likelihood calculation, MAP estimates, and ML estimation updates in polynomial time on SRTGs. We call this extension the center-surround algorithm. SRTGs extend mixture models by adding hierarchal structure that can vary across observations. The center-surround algorithm can recover the structure of observations, learn structure from observations, and classify observations based on their structure. We have used SRTGs and the center-surround algorithm to process both static images and dynamic video. In static images, SRTGs have been trained to distinguish houses from cars. In dynamic video, SRTGs have been trained to distinguish entering from exiting. We demonstrate how the structural priors provided by SRTGs support these tasks.

Joint work with Charles Bouman, Shawn Brownfield, Bingrui Foo, Mary Harper, Ilya Pollak, and James Sherman.

Note: Matt MacMahon and I have given over the reins of FAI to Prem Melville, Misha Bilenko, and Nick Jong. I had been doing it for 2 years, so it was time for me to move on, and Matt has been splitting his time between Austin and Berkeley, CA, where his wife is doing her pediatrics residency.