Rithesh Kumar

Machine learning enthusiast with a solid academic foundation in computer science, specializing in NeuroSymbolic AI, Generative AI and Natural Language Processing. Abundant expertise in developing and optimizing AI models across various industries, including finance, social media, and healthcare. Held a senior role as a machine learning decision scientist at Goldman Sachs. Enthusiastic about using my research skills and experience to drive innovation in AI.

Hyper-resolution of Compressed Whole-Slide Images for Automated Mitotic Figure Counting | Razvan's Lab

• Compressing and hyper-resolution of WSI of Breast Cancer cells using CycleGAN and Sparse NN models.
• Building the model for Mitotic Figure Counting on the compressed images to account for proliferation of the malignant tumor cells.

• Prostate Cancer Grading using Multistage Deep Neural Networks, MIND 2021, Springer: Developed a novel multi-stage deep learning framework for automated Gleason system grading (GSG) and grade group (GG) classification of prostate cancer cells, achieving an overall diagnostic accuracy exceeding 90% f1-score.
• Network Anomaly Detection using ANNs Optimised with PSO-DE Hybrid, SSCC 2018, Springer: Proposed a hybrid PSO-DE algorithm combining Particle Swarm Optimization and Differential Evolution to optimize ANNs for network anomaly detection. Obtained an accuracy of 98.7%, substantially improving the accuracy of conventional ANN-based methods.