« Why do we do Science? | Main | Can a computer think? »



I am a first-time visitor and from the looks of it, I will be a regular. I second Tom Mitchell's thoughts on the inspiration you derive from the brain. The motivational aspect of learning is surprisingly absent from ML, while it is taken to be critical and essential by people working on learning in the brain. As the amount of data to be analyzed inreases exponentially, a subsystem specifically desgined to weed out irrelevant data is important. However, the operating word 'irrelevant' is a tricky and complex one as it is not a static concept. It depends on current task and the like. The important thing to realize here is that the brain is not limited to solving a narrow domain of problems, and has not evolved specific modules for performing tasks in each sensory domain. As to your observation about the absence of any learning theories inspired by cognitive processes, there is Adaptive Resonance Theory, that has led to the development of classifiers like ARTMAP and its many flavors.

Jefferson Provost

"...the first successes for building flying machines were obtained when people stopped trying to imitate birds." I think this isn't strictly true. The concept of the airfoil, so essential to airplanes and helicopters, came from the study of bird's wings. I think the important message here is that in studying the brain, we should be looking for important computational principles of learning, rather than trying to imitate structure. When these principals are discovered they can be abstracted away from the structure and the resulting machine learning systems may look as different from brains as helicopters do from birds.

But you're also right, just as there are flying machines that don't use airfoils (blimps, rockets), there will be successful ML systems that don't use any computational principles from the brain.


Check out the work of thom grifiths, tenebaum, yale niv, nathaniel daw.......the list goes on. There is LOADS of interesting machine learning research going on at the intersection of ML and cognitive psychology, you just haven't looked hard enough.
Reinforcement Learning -> invented by psychologists


Hey, this is cool stuff, something worth my time. Good attempt. Quiet interesting way of narrating interesting stuff. I think you have spent a lot of time in researching as some of the facts were just so shocking and never heard of. I am speechless…

hollywood bistro

It always does. It's the root of learning.

buy viagra

I liked this blog, i think is very interesting, most of all for the new ideas that this blog talk.

christian louboutin knockoffs

I did a little research on the topic and found that most people agree with your blog. Thanks.

The comments to this entry are closed.