Name: Prathyusha Akundi
Type: User
Company: International Institute of Information and Technology Hyderabad (IIITH)
Bio: I'm a Medical Image Processing researcher working under guidance of Prof. Jayanthi Sivaswamy at IIITH
Location: Hyderabad, India
Blog: https://www.linkedin.com/in/prathyusha-akundi-69912796/
Prathyusha Akundi's Projects
Implementation for the paper "Adversarial Continual Learning" in PyTorch.
The repository for the project code for my course Angular Essential Training
Interpreting Bayesian inference as continual learning with a CNN
Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
The Microsoft Bot Builder SDK is one of three main components of the Microsoft Bot Framework. The Microsoft Bot Framework provides just what you need to build and connect intelligent bots that interact naturally wherever your users are talking, from text/SMS to Skype, Slack, Office 365 mail and other popular services.
Welcome to the BotBuilder samples repository. Here you will find task-focused samples in C# and Node.js to help you get started with the Bot Builder SDK!
A brain-inspired version of generative replay for continual learning with deep neural networks (e.g., class-incremental learning on CIFAR-100; PyTorch code).
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error = 0.34%.
The manuscript has been accepted in TMI.
WWW 2018 paper: CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information
Continual learning of neural networks with 11 state-of-the-art methods and 4 baselines. Codebase of the continual learning survey: "A continual learning survey: Defying forgetting in classification tasks." arXiv preprint arXiv:1909.08383 (2019)."
CMS Medicare Fraud Detection
PGDDS Capstone Project
Evaluate three types of task shifting with popular continual learning algorithms.
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [Inoue+, CVPR2018].
Project for Data Mining course
A Pytorch implementation of the paper `Deep Autoencoding Gaussian Mixture Model For Unsupervised Anomaly Detection` by Zong et al.
This contains an implementation of the SeGAN model for semantic segmentation introduced in https://arxiv.org/pdf/1703.10239.pdf
Deep Extreme Cut http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr
Differentiable neural computer experiments
Differentiable Neural Computer - A Pure NumPy Implementation
End-to-End Incremental Learning