Hello. I'm Nikhil, I am a Computer Science undergrad, Machine learning research scholar and a developer who tries to solve real life challenges in the most productive way through my technical skills and fundamental knowledge. I am always ready to learn and grow. Scroll down to take a look at my projects, publications and experiences. More..
Worked with the AITS community on their Open-Source DNNC (Deep Neural Network Compiler) and the DNNC operators. Build operators in C++ and implemented the Python interface and testing. Studied ONNX operators and design for implementing them for DNNC and Eigen tensors library.
Build machine learning and deep learning models to provide solutions to real-life challenge - dengue disease prediction. Achieved 197th rank worldwide in ML competition hosted by DrivenData as a part of the internship. Won the hackathon conducted among the interns.
A freelancing work which includes solving tough and interesting problems posted by students from all around the world in the most elaborative and descriptive way making the learning easy. Helping Chegg community to increase their daily answering counts.
In this research we proposed a novel model twofold linear regression which out perform compare to all previous models. Moreover, we have analyzed various neural network, support vector machine, random forest, boosted tree, XGBoost based predictive models and evaluate their performance against proposed method.
In this research we presented our work on Deep Neural Network Compiler also known as DeepC which includes design and implementation of operators and functions. The paper is a theoretical understanding of the workflow of the compiler. The paper got selected as a poster to be presented at ACM conference held at IIT, Gandhinagar.
This research has conducted a study on rainfall pattern in Indian states using machine learning techniques and algorithms, which utilizes government provided rainfall data from 1901-2017. This research proposes a study and analysis of rainfall in the Indian states and compared their performances to the standard results.