Name: Ashwin De Silva
Type: User
Company: Johns Hopkins University
Bio: PhD student at Johns Hopkins. Machine Learning, Statistics, and Deep Learning.
Twitter: AshwindeSilva1
Location: Baltimore, MD
Blog: https://laknath1996.github.io/
Ashwin De Silva's Projects
Create a virtual spherical phantom and takes a given number of 2D slices from it and reconstructs the phantom using the sliced 2D binary images.
A paper investigating bilateral symmetry of connectome networks.
A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
Summer course content for Neuromatch Academy
Code for the EN.520.648 Compressed Sensing & Sparse Recovery group project
Latest version of my CV.
This repository Introduces a joint convolutional and spatial quad-directional LSTM (SQD-LSTM) network for phase unwrapping in 2D images.
Work on retinal and scleral image understanding (in progress)
Hobby iOS Project 😁
Diffusion MR imaging in Python
DMRITool is an open souce toolbox for reconstruction, processing and visualization of diffusion MRI data (DWI, tensor, ODF,EAP, fibers etc.).
The project was conducted as a part of the module Digital Signal Processing EN2570. The objective was to design a Non - Recursive (Finite Impulse Response) Bandstop Filter using the Kaiser Window Function. MATLAB 2014a software package was used as the programming environment for the design project.
Gated graph convolutional recurrent neural networks code used in:
Course project for EN.553.741 Machine Learning II at JHU. Implements Wasserstein GAN, variational autoencoder and denoising diffusion probabilistic models.
Includes the scripts and data used for promoter search methods.
This repository includes the verilog files used for the designing of an image downsampling custom processor.
This repository includes the MATLAB Scripts which perform various Image Processing Techniques. The codes were generated as required by the EN2550 Fundamentals of Image Processing and Machine Vision Module offered in the Department of Electronic and Telecommunication Engineering at the University of Moratuwa.
iris-plot is a tool written in MATLAB to visualize the gain of function or the loss of function in terms of the p-value from the two-sample unpaired t-test performed upon the patient and control data.