Harsh Agarwal
Angestellt, Master's Thesis, Bosch Engineering GmbH
Student, Data Science & Artificial Intelligence, Universität des Saarlandes
Stuttgart, Deutschland
Suchst Du einen anderen Harsh Agarwal?
Über mich
I am a passionate and driven professional with a strong background in Computer Science and expertise in Deep Learning, Computer Vision, and Artificial Intelligence. With an ongoing Master's degree in Data Science & Artificial Intelligence (graduation in Oct. 2023), I have successfully tackled challenging R&D problems and contributed to cutting-edge projects in the field. My experience includes optimizing automotive RADAR Pointcloud Networks and developing deep learning-based location networks. I am keen about staying at the forefront of technological advancements and always eager to explore new opportunities and collaborate on innovative projects. Let's connect and engage in meaningful discussions and share insights.
Werdegang
Berufserfahrung von Harsh Agarwal
The primary focus is to embed hierarchical class labels for accurate object classification of automotive RADAR 3D point cloud. • Researched the impact of multiple embedding strategies in both Euclidean & Hyperbolic Space, leveraging the intrinsic semantic hierarchy • Integrated entropy based multi-level network modifications enabling adaptive collaboration & information sharing Supervisors: - Dr. Martin Elmer and Mr. Raphael Kolk, Bosch - Prof. Philipp Slusallek and Dr. Christian Müller, DFKI
• Implemented Confidence Estimation Network over trained model, to estimate the prediction confidence for improved post processing • Developed novel location stacking algorithm with a ring buffer for the production code
2 Jahre und 3 Monate, Juli 2019 - Sep. 2021
Software Engineer
Robert Bosch Engineering and Business Solutions LimitedNext Generation RADAR • Developed a novel DeepLoc Network that performs object type classification on point-cloud from automotive RADAR • Created metrics for efficient testing of classification model for the Automatic Emergency Braking use-case Synthetic Traffic Sign Generator • Developed the pipeline to deal with data-imbalance problem with hundreds of classes for traffic sign image classifier • Used conventional techniques like affine transformation, background blending for a deterministic generation
7 Monate, Mai 2018 - Nov. 2018
Deep Learning Intern
Canon India Software Development Center
• Optimized and translated Classification and Segmentation models for faster computation on Jetson TX2 using TensorRT in the half-precision mode • Reduced model's final inference time by about 70% with 0.5% change in accuracy • Worked with YOLO v3 model for head detection in sports dataset
Ausbildung von Harsh Agarwal
Bis heute 2 Jahre und 9 Monate, seit Okt. 2021
Data Science & Artificial Intelligence
Universität des Saarlandes
3 Jahre und 11 Monate, Juli 2015 - Mai 2019
Electronics and Communication Engineering
Indian Institute of Information Technology, Design and Manufacturing, Jabalpur
Sprachen
Englisch
Fließend
Deutsch
Grundlagen