fbpx

Tag Archive for programming

Public Speaking at the IGDA

July 17, 2016 Videogames Comments Off on Public Speaking at the IGDA

I was invited to give a talk to the IGDA in partnership with DAGA in Salt Lake City a couple of months ago. Had a wonderful time! They were kind enough to record my talk (I do a lot of talks, but I don’t always get to see how they turned out from the audience perspective, so this is especially cool for me).

Check it out!

Back when I started, there was no clear path into the games industry. You got there by asking around, talking to people, finding ads in the back of local newspapers, showing up for a night of tabletop gaming with the right group of people. While the idea of working in games has become mainstream over the past few decade, I find that a lot of students still think of it as a rather monolithic entity. They get hung up on the idea of having the *perfect* skill for this job or that job, where the reality is, there are a LOT of different niches in games and, if you have spent the time to develop skills that apply, even if you don’t have a degree, you have a chance to find a home here.

Neural nets and modular capabilities

April 19, 2015 future, Writing Comments Off on Neural nets and modular capabilities

http://journals.plos.org/ploscompbiol/article?id=10.1371%2Fjournal.pcbi.1004128

This abstract, as it was originally presented via one of the science aggregation websites, was about robots.

Except it wasn’t.  Not really.  I mean, “robots” is the end goal that most people will understand, but what these people are examining is the way that memories are written and rewritten.  They are examining adaptation of the learning process and how that can be applied to the idea of building neural networks.

Right now, when we build an AI, whether it be to assemble cars or act as an enemy in a videogame, it’s very task based.  In an ultra-simplified form you get, “If this happens, you deliver that result.”

But this not only leaves holes in the logic (because what if THAT happens and you didn’t think of it beforehand?) but it makes the programming rigid.  The AI can only operate according to the rules you have set, so if a dog runs into the automotive assembly factory, or a player decides to sneak around the left side of the building instead of the right, you end up with a broken situation.

There is a risk (seemingly) that as we continue to develop neural network based AI’s that this will get coded in there too.  Not always on purpose, but because that is familiar ground.  It is something we can test easily.  It is something we can codify and deliver a clear result that can be shown to colleagues/investors, etc. to keep the funding and interest going.

But in order to truly make a neural net efficient at learning and executing new tasks, it’s got to retain the old tasks.  It’s got to use the knowledge it already has the learn the new stuff even faster (rather than having it handed to them in the form of a programming block).

 

« Older Entries