RetroSpectra is a real-time facial emotion detection application. It uses Convolutional Neural Network (CNN) to identify human emotions from live video feed. The application leverages a pre-trained model to accurately detect and classify emotions, providing an interactive and engaging user experience.

American Sign Language (ASL) Detection using CNN

A web-based AI application capable of detecting and attributing AI Art.

Deployment of Facial Emotion Model

This repository offers a robust solution for multilabel image classification. Utilizing advanced neural networks like VGG16, VGG19, ResNet50, InceptionV3, DenseNet121, and MobileNetV2, the project achieves precise classification across 107 diverse categories.

Depth estimation with neural network, and learning on RGBD images

My notes and solutions for the 'Deep Learning Specialization' by DeepLearningAI,

This is a repository hosting all code and models detailed in the article Computational limits to the legibility of the human brain.

Practice Convolutional Neural Network using Keras | Hyperparameter Tuning

Practice hyper parameter tuning in Neural Network.

Explore advanced deep learning applications with Tensorflow in soil spectroscopy with two coursework projects. Achieved superior model performance, uncovering insights for future enhancements and model optimisation.

Aplikasi pengenalan tulisan tangan Aksara Simalungun. Menggunakan AI sebagai backend yang dapat secara otomatis mendeteksi karakter.

My official portfolio for visual demonstrations of my work and projects on vehicle controls, software testing, robotic simulations, AI and web development.

The project aims to build strong CNN image classification models to automatically predict the location of the image based on any landmarks depicted in an image.

This a repo for the projects I completed during my Deep Learning Udacity Nanodegree.

This repository contains implementation and evaluation scripts for various pre-trained deep learning models applied to binary classification of cats and dogs using transfer learning on a balanced dataset. Explore different architectures such as VGG16, VGG19, ResNet50, InceptionV3, DenseNet121, and MobileNetV2 fine-tuned for accurate classification.

All my Academic & Non-Academic Projects are stored here.

Python marine animal photo recognition app using Convolution Neural Network in deep learning

"TensorFlow Image Classification Project" This project demonstrates image classification using TensorFlow. The CIFAR-10 dataset, consisting of 60,000 32x32 color images across 10 classes, is explored and analyzed. Key components include data loading, dataset characteristics, and a machine learning model built using the functional API.