A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
Techniques for deep learning with satellite & aerial imagery
Implementation of Action Recognition using 3D Convnet on UCF-101 dataset.
Temporal Segments LSTM and Temporal-Inception for Activity Recognition
Temporal augmentation with two-stream ConvNet features on human action recognition
Automated methods to detect and classify human diseases from medical images, using Deep Neural Networks
Identification of Farsi (Arabic) Scanned Handwritten Digits
Optical character recognition of Farsi and Arabic letters
Group Emotion Recognition using deep neural networks and Bayesian classifiers.