Wednesday, October 14, 2009

Computer Science in Neuroscience

I got a job basically through a fellowship which wanted to bring in graduates in Computer Science to look at biological problems. For the past 9 months I have been looking at brain image data especially Diffusion Tensor Data trying to do basic processing and also applying classification methods and developing segmentation methods with several collaborators. Because of the channel I was hired through and because of the circle I am spending my working (and social) hours I can clearly see how Neuroscience (and biology in general) can drastically benefit from CS wisdom. It's an intriguing thing that our quest for machines laid the foundation to understand their language which in turn gave a fresh perspective for the foundation of modern science that in turn can help define our understanding of life.

CS wisdom can affect research pace in neuroscience on many many different levels. Just by applying software engineering skills you can grease a lot of processing. Machine learning/data mining/Artificial Intelligence methods can obviously help making sense of the biological sensor data. CS wisdom can help apply blackbox type research style to start making progress. This wisdom is almost always the fundamental tool in complexity theory: we need to start somewhere for the general problem setting and then dig deeper to exploit specific instances of problems as needed. One thing I noticed is that lack of such perspective can hold back lot of progress. Also another wisdom you can get from CS scientists like Umesh Vazirani is to focus on higher order bits. Well as I mentioned in my previous post building bridges for wisdom between CS and Neuroscience is allowing me some good times.

No comments: