• AI/ML, LLM, Summarization, Search & Autosuggestion

• Developed Machine Learning models using Random Forest, XGBoost and LightGBM on features extracted on Retina Datasets. Performed Hyperparameter Optimization using Bayesian Optimization.• Developed Deep Learning CNN models for Binary Classification, Multi-class Classification and Multi-label Classification on Retina Datasets and Chest X-Ray Datasets.• Involved in the deployment of models using Docker and AWS.

• The goal was to find the number of specified prototype instances (texture-less objects) in the scene image, using Matlab.• This was done using a sequence of processes of edge detection, segmentation, bounding-box generation and size thresholding, feature extraction, classification, and counting and localization.• Different classifiers were used, and Tree-Bagger with 50 trees was found to outperform the other methods.• The work resulted in a conference paper entitled "Vision based Counting of Texture-less Objects using Shape and Color Features", accepted at the proceedings of ICIIS 2016.