KateCode & data accompanying the KDD 2017 paper "KATE: K-Competitive Autoencoder for Text"
Stars: ✭ 135 (+159.62%)
Alae[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+6011.54%)
tldrTLDR is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses
Stars: ✭ 95 (+82.69%)
NMFADMMA sparsity aware implementation of "Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence" (ICASSP 2014).
Stars: ✭ 39 (-25%)
auto-gfqgAutomatic Gap-Fill Question Generation
Stars: ✭ 17 (-67.31%)
Relation-Network-PyTorchImplementation of Relation Network and Recurrent Relational Network using PyTorch v1.3. Original papers: (RN) https://arxiv.org/abs/1706.01427 (RRN): https://arxiv.org/abs/1711.08028
Stars: ✭ 17 (-67.31%)
extra-modelCode to run the ExtRA algorithm for unsupervised topic/aspect extraction on English texts.
Stars: ✭ 43 (-17.31%)
twicTopic Words in Context (TWiC) is a highly-interactive, browser-based visualization for MALLET topic models
Stars: ✭ 51 (-1.92%)
torch-metricsMetrics for model evaluation in pytorch
Stars: ✭ 99 (+90.38%)
tassalTree-based Autofolding Software Summarization Algorithm
Stars: ✭ 38 (-26.92%)
VisualMLInteractive Visual Machine Learning Demos.
Stars: ✭ 104 (+100%)
KGE-LDAKnowledge Graph Embedding LDA. AAAI 2017
Stars: ✭ 35 (-32.69%)
photometric optimizationPhotometric optimization code for creating the FLAME texture space and other applications
Stars: ✭ 271 (+421.15%)
QuestionClusteringClasificador de preguntas escrito en python 3 que fue implementado en el siguiente vídeo: https://youtu.be/qnlW1m6lPoY
Stars: ✭ 15 (-71.15%)
Product-Categorization-NLPMulti-Class Text Classification for products based on their description with Machine Learning algorithms and Neural Networks (MLP, CNN, Distilbert).
Stars: ✭ 30 (-42.31%)
converseConversational text Analysis using various NLP techniques
Stars: ✭ 147 (+182.69%)
NoisyStudent"Self-training with Noisy Student improves ImageNet classification" pytorch implementation
Stars: ✭ 31 (-40.38%)
ctpfrecPython implementation of "Content-based recommendations with poisson factorization", with some extensions
Stars: ✭ 31 (-40.38%)
learning-stmLearning structural topic modeling using the stm R package.
Stars: ✭ 103 (+98.08%)
amazon-reviewsSentiment Analysis & Topic Modeling with Amazon Reviews
Stars: ✭ 26 (-50%)
haskell-vaeLearning about Haskell with Variational Autoencoders
Stars: ✭ 18 (-65.38%)
nlp classificationImplementing nlp papers relevant to classification with PyTorch, gluonnlp
Stars: ✭ 224 (+330.77%)
catseyeNeural network library written in C and Javascript
Stars: ✭ 29 (-44.23%)
DAF3DDeep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound
Stars: ✭ 60 (+15.38%)
lda2vecMixing Dirichlet Topic Models and Word Embeddings to Make lda2vec from this paper https://arxiv.org/abs/1605.02019
Stars: ✭ 27 (-48.08%)
head-qaHEAD-QA: A Healthcare Dataset for Complex Reasoning
Stars: ✭ 20 (-61.54%)
deep-stegGlobal NIPS Paper Implementation Challenge of "Hiding Images in Plain Sight: Deep Steganography"
Stars: ✭ 43 (-17.31%)
FedLab-benchmarksStandard federated learning implementations in FedLab and FL benchmarks.
Stars: ✭ 49 (-5.77%)
autoencoders tensorflowAutomatic feature engineering using deep learning and Bayesian inference using TensorFlow.
Stars: ✭ 66 (+26.92%)
Twitter-TrendsTwitter Trends is a web-based application that automatically detects and analyzes emerging topics in real time through hashtags and user mentions in tweets. Twitter being the major microblogging service is a reliable source for trends detection. The project involved extracting live streaming tweets, processing them to find top hashtags and user …
Stars: ✭ 82 (+57.69%)
autoencoder for physical layerThis is my attempt to reproduce and extend the results in the paper "An Introduction to Deep Learning for the Physical Layer" by Tim O'Shea and Jakob Hoydis
Stars: ✭ 43 (-17.31%)
SpinNet[CVPR 2021] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Stars: ✭ 181 (+248.08%)
Walk-TransformerFrom Random Walks to Transformer for Learning Node Embeddings (ECML-PKDD 2020) (In Pytorch and Tensorflow)
Stars: ✭ 26 (-50%)
TopicNetInterface for easier topic modelling.
Stars: ✭ 127 (+144.23%)
time-series-autoencoder📈 PyTorch dual-attention LSTM-autoencoder for multivariate Time Series 📈
Stars: ✭ 198 (+280.77%)
Encoder-ForesteForest: Reversible mapping between high-dimensional data and path rule identifiers using trees embedding
Stars: ✭ 22 (-57.69%)
JoSH[KDD 2020] Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding
Stars: ✭ 55 (+5.77%)
attention-sampling-pytorchThis is a PyTorch implementation of the paper: "Processing Megapixel Images with Deep Attention-Sampling Models".
Stars: ✭ 25 (-51.92%)
SPANSemantics-guided Part Attention Network (ECCV 2020 Oral)
Stars: ✭ 19 (-63.46%)
SelfOrganizingMap-SOMPytorch implementation of Self-Organizing Map(SOM). Use MNIST dataset as a demo.
Stars: ✭ 33 (-36.54%)
simclr-pytorchPyTorch implementation of SimCLR: supports multi-GPU training and closely reproduces results
Stars: ✭ 89 (+71.15%)
DualStudentCode for Paper ''Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning'' [ICCV 2019]
Stars: ✭ 106 (+103.85%)
gensimr📝 Topic Modeling for Humans
Stars: ✭ 35 (-32.69%)
MelNet-SpeechGenerationImplementation of MelNet in PyTorch to generate high-fidelity audio samples
Stars: ✭ 19 (-63.46%)
mauiMulti-omics Autoencoder Integration: Deep learning-based heterogenous data analysis toolkit
Stars: ✭ 42 (-19.23%)
ElasticFaceOfficial repository for ElasticFace: Elastic Margin Loss for Deep Face Recognition
Stars: ✭ 86 (+65.38%)
BTMBiterm Topic Modelling for Short Text with R
Stars: ✭ 78 (+50%)
kg one2setCode for our ACL 2021 paper "One2Set: Generating Diverse Keyphrases as a Set"
Stars: ✭ 58 (+11.54%)
TensorFlow-AutoencodersImplementations of autoencoder, generative adversarial networks, variational autoencoder and adversarial variational autoencoder
Stars: ✭ 29 (-44.23%)
lowshot-shapebiasLearning low-shot object classification with explicit shape bias learned from point clouds
Stars: ✭ 37 (-28.85%)