🧠 Classify brain tumors in your browser with BrainVision AI — a fast, privacy-focused tool using client-side machine learning for accurate diagnostics.

Advanced deep learning learning techniques, layers, activations loss functions, all in keras / tensorflow

A series of machine learning and deep learning projects in finance.

The project "Lung Cancer Detection Using CNN" focuses on developing a deep learning-based approach for early and accurate detection of lung cancer using medical imaging data such as CT scans or X-rays. Early detection is critical for improving survival rates and treatment outcomes.

A lightweight header-only library for using Keras (TensorFlow) models in C++.

Fast and accurate AI powered file content types detection

MiniRes is a small Python library + pretrained ensemble model that predicts resin usage in grams for pre-supported 3D printed miniatures.

BrainVision AI is a fully client-side brain tumor classifier that runs entirely in the browser using ONNX Runtime Web. It processes MRI images locally, preserving privacy while delivering fast and reliable predictions. The project includes a responsive UI, multi-language support, theme switching, and a complete training pipeline with Keras and ONNX

Proyecto de la materia avance tecnológico iutepi

All about creating a dataset, preprocessing images, and creating an actual model to solve captcha

Telecom Churn Prediction Model using ANN

Serving a keras model (neural networks) in a website with the python Django-REST framework.

Contains lab exercises for deep learning using TensorFlow and Keras done in semester 6 of college.

Mayabati is a personal AI chef designed for enhancing culinary experience. Crafted by Biswadeb Mukherjee, a leading developer of ParseSphere Innovations.

A Keras port of Detector of Rotatable Bounding Boxes

A deep learning model designed for sentiment analysis by leveraging the power of ResNet and GoogleNet-inspired architectures. This hybrid model efficiently extracts high-level semantic features from textual data to classify sentiments into Positive, Negative, or Neutral categories.

This project aims to classify brain MRI images into four categories: Glioma, Meningioma, No tumor, and Pituitary tumor. It utilizes TensorFlow to build and train a convolutional neural network (CNN) for the task.

Predicting patient medicine costs using deep learning (FNN) with a clean Streamlit dashboard.

This project classifies internet memes using multimodal learning by combining textual and visual features. It performs offensive content detection and emotion classification leveraging the MultiOFF and Memotion-7k datasets. The model integrates ALBERT for text, VGG-11 for images, and BLIP-generated captions to improve understanding of meme sentimen

Code for the paper "Transfer Learning for Facial Attribute Prediction and Clustering" (iSCI 2019)