Atreya Shankar

mv-temporal-rgan. Multivariate recurrent GANs aimed at generating biomedical time-series. Methodology involves drawing symmetries to adversarial image generation

i3-balance-workspace. Balance windows and workspaces in i3wm

clingo-solvers. Answer Set Programming (ASP): clingo solvers for NxN Sudoku, Yosenabe, Minotaur and Elevator games

spam-detection. Investigating whether sequential learning is inherently important for the task of spam classification, through a comparison of SVM vs. CNN-LSTM models

spp-explainability. SoPa++: Leveraging explainability from hybridized RNN, CNN and weighted finite-state neural architectures

semantic-isometry-nmt. Investigating the isometric behaviour of Neural Machine Translation models on binary semantic equivalence spaces

deep-generative-models. Deep generative models implemented with TensorFlow 2.0: eg. Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Deep Boltzmann Machine (DBM), Convolutional Variational Auto-Encoder (CVAE), Convolutional Generative Adversarial Network (CGAN)

memory-daemon. Memory-daemon for remote RAM management with email alerts

sentiment-argument-mining. Sentiment analysis and argumentation mining in UNSC Speeches