I am a Computer Science graduate from University of Southern California. I have expertise in building products which mainly involve the use of supervised object detection, few-shot image or video classification, semantic segmentation and even one-shot image classification. My academic background includes coursework in Analysis of Algorithms, Foundations of AI, NLP, and Database Systems, providing me a solid foundation in computer science.

I have even worked on financial data in my internship and used Gradient Boosting Methods to predict user behavior. In my work at USC's SPORT Lab I focused on optimizing neural network training with the help of multiprocessing paradigms in pytorch.

In addition to my academic and professional experience, I have done some personal projects in multimodal deep learning employing the use of BERT. One of my notable projects involves identifying plot holes in stories using BERT and Graph Neural Networks.

Additionally I have also implemented GAN and VAE in my personal project and school assignment and have working knowledge of GPT.

Bhalekar, M., Sureka, S., Joshi, S., Bedekar, M. (2020). Generation of Image Captions Using VGG and ResNet CNN Models Cascaded with RNN Approach. In: Agarwal, S., Verma, S., Agrawal, D. (eds) Machine Intelligence and Signal Processing. MISP 2019. Advances in Intelligent Systems and Computing, vol 1085. Springer, Singapore. https://doi.org/10.1007/978-981-15-1366-4_3