Partha Pratim Saha

robustNN-transformers

June 8, 2026 – Present

Robust Neural Learning via S-Divergence: ViT + BERT + CLIP benchmarks with interactive 3D visualizations. Extends rSDNet (arXiv:2603.17628) to Transformers across medical imaging and clinical NLP.

nDNA-v1

October 4, 2025 – Present

nDNA-v1 — GitHub repository

ImageCaptioning

November 17, 2021 – November 30, 2021

Image Captioning is the process of generating textual description of an image. It uses both Natural Language Processing and Computer Vision to generate the captions. The dataset will be in the form [image to captions]. The dataset consists of input images and their corresponding output captions. Encoder The Convolutional Neural Network can be thought of as an encoder. The input image is given to CNN to extract the features. The last hidden state of the CNN is connected to the Decoder. Decoder The Decoder is a Recurrent Neural Network(RNN) which does language modelling up to the word level. The first time step receives the encoded output from the encoder and also the START vector using Use Pretrained Resnet-50 model trained on ImageNet dataset (available publicly on google) for image feature extraction and created 4 layered RNN layer model and other relevant layers for image caption generation

pps121.github.io

November 7, 2021 – Present

pps121.github.io — GitHub repository

Python-ML-_Work

May 28, 2020 – June 8, 2022

Day-to-day work and findings on interesting things

Partha.github.io

September 30, 2019 – September 30, 2019

Partha.github.io — GitHub repository

HelloWorld

January 12, 2017 – January 12, 2017

HelloWorld — GitHub repository

demo

January 10, 2017 – January 10, 2017

demo — GitHub repository

hello-world

January 9, 2017 – January 9, 2017

Demo hello-world

DemoDrupal

January 9, 2017 – January 10, 2017

DemoDrupal — GitHub repository