New Life and Interests
‘Hello World’ from my Medium account! I’m (somewhat) committed to infuse some vigor into my writing and this is the first step towards it. This space would serve as my blog where I would write about my personal, academic and professional interests as well as developments that excite me.
I’m majoring in Electrical Engineering, focusing on Computer Vision. People around always ask me why I don’t build circuits and work on hardware. I put my thought to this question a few years ago and realized an important underlying reason for the same. I believe that semiconductors are already quite in an advanced state, but we could still create new and improve existing algorithms to make chips function at their full potential (which they definitely aren’t today).
Computer Vision is concerned with processing images to produce a symbolic representation of objects in the world. It is actually teaching your computer to see and interpret the world like we humans do. This field encompasses several categories and has ubiquitous practical applications. I’m primarily interested in leveraging methods from machine learning and optimization to develop algorithms for semantic understanding of images and related multimedia content. Automated methods for such detailed analysis of images are essential for most applications such as image search, organization of photo collections, and large-scale analysis of the content of media collections for advertisement.
This is still a very open field with scientific challenges that have intrigued researchers for the last four to five decades. There exists no system today that can come close to emulating the capabilities of humans. If we did not have a proof of existence of a very powerful, general and flexible system in our own retinas and visual cortices, the research of the past quarter of a century would seem to indicate that the task of building robust vision systems is hopeless! This underscores the problem — we know that it can be solved, yet we do not know how to solve it well. I’m also excited about foraying into unknown territory and analyzing inputs from various inter-related areas such as language processing, cognitive science, and human-computer interaction, to solve the general vision problem. In this process, we could aim to find answers to deep and fundamental questions about representation and computation at the core of human intelligence.
I firmly believe that Computer Vision is Artificial Intelligence.
Note: Most of the content of this post has been ported from my old blog.