Introduction Link to heading
Hi new readers! I am Rishab Mudliar and I am currently in the final year of my Computer Science Major. This blog is part of a series dedicated to noting down my activities during the period of Google Summer of Code.
GSoC Link to heading
Google Summer of Code or the acronym GSoC is a program aimed at people in tech looking to contribute to open-source software development. Selected contributors work for 12+ weeks on projects that solve interesting problems. This year I will be working under Red Hen Lab and solving an interesting problem under their guidance.
My project Link to heading
Describing a well-defined piece of art can be a daunting task as it requires robust understanding of the concepts of the art, the styles and the strokes of the artist. Art historians such as Emile Male have spent massive amounts of time in order to gain sound understanding of Chrsitian artistry as a result of which these paintings are now captioned and understandable by junior historians and even the general population.
But can this knowledge be passed on? In order to generate sound descriptions of art, a historian might have to study extensively on it. Is it possible to reduce this burden?
The usefulness of Machine Learning lies in it’s ability to learn from data without being explictly programmed. If we were to apply this in the arena of art then it would mean that by leveraging the captions generated by historians we could build an automated tagging tool. While, this won’t replace historians, it would still be an effective way to solve some of the problems previously discussed.
This week Link to heading
- The first thing that happened this week was of course the acceptance letter which was honestly an amazing feeling.
- After that Professor Mark Turner asked us to give our basic details in order to update it on their projects page.
Next week Link to heading
- Probably attending the orientation when that occurs which will give me a chance to interact with my mentors hopefully!
- I plan on reading some papers/blogs related to curation of dataset since this is a fairly new thing to me.