Tensorflow Mnist CnnMNIST classification using Convolutional NeuralNetwork. Various techniques such as data augmentation, dropout, batchnormalization, etc are implemented.
Densenet Sdrrepo that holds code for improving on dropout using Stochastic Delta Rule
Lstms.pthPyTorch implementations of LSTM Variants (Dropout + Layer Norm)
IcellrSingle (i) Cell R package (iCellR) is an interactive R package to work with high-throughput single cell sequencing technologies (i.e scRNA-seq, scVDJ-seq, ST and CITE-seq).
CplxmoduleComplex-valued neural networks for pytorch and Variational Dropout for real and complex layers.
Svhn CnnGoogle Street View House Number(SVHN) Dataset, and classifying them through CNN
Variance NetworksVariance Networks: When Expectation Does Not Meet Your Expectations, ICLR 2019
Satania.moeSatania IS the BEST waifu, no really, she is, if you don't believe me, this website will convince you
DropblockImplementation of DropBlock: A regularization method for convolutional networks in PyTorch.
DeepnetImplementation of CNNs, RNNs, and many deep learning techniques in plain Numpy.
dropclass speakerDropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020
CS231nMy solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition
DropoutsPyTorch Implementations of Dropout Variants
ALRAImputation method for scRNA-seq based on low-rank approximation