mughanibu

Deep-Learning-for-Inverse-Problems

This project hosts the code and datasets I used for Deep Learning course at Boston University. It aims to post-process the images the low quality images produced as a result of solving inverse problems in imaging (particularly Computed Tomography) and produce high-quality images.

DeepMAR

This repository hosts the training code and links to trained models and training datasets used in our article "Fast Enhanced CT Metal Artifact Reduction using Data Domain Deep Learning", accepted for publication in the IEEE Transactions on Computational Imaging.

Dendritic-Spine-Analysis-Dataset

A fully annotated dataset of Two-Photon Laser Scanning Microscopy (2PLSM) images of three types of dendritic spines. We make a standard dendritic analysis dataset publicly available including raw data, manual annotations, and manual labels.

Alexnet_SkinLesion

cs591s2

CS591-S2: Deep Learning, Spring 2017, Boston University

hugo-academic

The website designer for Hugo. Build and deploy a beautiful website in minutes :rocket:

mughani_web_academic

Non_Parametric_Kernel_Density_Estimation

We propose to use a kernel density estimation (KDE) based approach for classification. This non-parametric approach intrinsically provides the likelihood of membership for each class in a principled manner.

tensorflow-vdsr

A tensorflow implementation of "Accurate Image Super-Resolution Using Very Deep Convolutional Networks", CVPR 16'