Community Bonding period ended last week and my first blog is based on the work carried out in the last week. My meeting with GSOC mentors at the start of the week helped me chalk out an agenda for the week. As the first step, I familiarized myself with Tensorflow  operations, functions and distribution strategies. My previous experience with PyTorch as  well as `website tutorials` on basic Deep Learning models helped me quickly learn Tensorflow. As the next step, I read VQ-VAE paper &  understood the tensorflow open source implementation. VQ-VAE addresses 'posterior collapse'  seen in traditional VAEs and overcomes it by discretizing latent space. This in turn also  improved the generative capability by producing less blurrier images than before.  Familiarizing about VQ-VAE early on helps in understading the latents used in Diffusion models in later steps. I also explored a potential dataset - `IXI (T1 images) ` - and performed some exploratory data analysis, such as age & sex distribution. The images contain  entire skull information, it may require brain extraction & registration. It maybe more useful  to use existing preprocessed datasets & align them to a template. For next week, I'll be  conducting further literature survey on Diffusion models.

GSOC 2023 week 0 blog

While applying for the GSOC 2023 DIPY sub-project titled “Creating Synthetic MRI”, I knew this would be the right one for me for two reasons. Keep reading to know more!
 

As nervous and not-so-optimistic as I am about applying for academic competitions, I pushed myself to apply for GSOC out of a necessity for summer job more than anything. This got me out of my comfort zone and I ventured into open source development. During the time of application I was a Master’s student from NYU(current status - graduated) with focus on Deep Learning Applications in Healthcare. I was so involved in research in Computer Vision during school, I decided to pursue career in the same field going forward. Fortunately, I came across a college senior’s post on LinkedIn regarding getting accepted as a mentor for GSOC 2023 during that time. This prompted me to look further into GSOC and its list of projects for this year. I have only heard of GSOC during my undergrad, during which I never could muster courage to pursue something outside college. But this time around, I decided to put a confident front and take the leap.

As I searched through the list of available projects, I got iteratively definitive about what I wanted to work on - looked for python projects first, filtered out machine learning projects next, narrowed down to a couple of relevant projects. In the process, I came across the list of DIPY projects. Firstly, I was looking to further my research knowledge in ML by exploring Generative AI. Secondly, I have worked with MRI datasets in the context of Deep Learning previously, so ‘Creating Synthetic MRI’ project seemed the right fit. These reasons got me hooked to DIPY sub-organization. I thoroughly enjoyed exploring DIPY applications and began the process for the application preparation soon. With the wonderful help from the mentors, I successfully submitted an application, later got an interview call and voila, I got in!

I am very happy about participating in GSOC this year. What started out as a necessity has now become a passion project. I hope to enjoy the journey ahead, looking forward to learning and implementing few things along the way!