NeurolibEasy whole-brain modeling for computational neuroscientists π§ π»π©πΏβπ¬
Stars: β 188 (-49.73%)
EhcfThis is our implementation of EHCF: Efficient Heterogeneous Collaborative Filtering (AAAI 2020)
Stars: β 70 (-81.28%)
BlinkdlA minimalist deep learning library in Javascript using WebGL + asm.js. Run convolutional neural network in your browser.
Stars: β 69 (-81.55%)
TorchganResearch Framework for easy and efficient training of GANs based on Pytorch
Stars: β 1,156 (+209.09%)
reefAutomatically labeling training data
Stars: β 102 (-72.73%)
LovaszsoftmaxCode for the LovΓ‘sz-Softmax loss (CVPR 2018)
Stars: β 1,148 (+206.95%)
Handwriting GenerationImplementation of handwriting generation with use of recurrent neural networks in tensorflow. Based on Alex Graves paper (https://arxiv.org/abs/1308.0850).
Stars: β 361 (-3.48%)
Deep ReviewA collaboratively written review paper on deep learning, genomics, and precision medicine
Stars: β 1,141 (+205.08%)
KekasJust another DL library
Stars: β 178 (-52.41%)
Stanford Cs231Resources for students in the Udacity's Machine Learning Engineer Nanodegree to work through Stanford's Convolutional Neural Networks for Visual Recognition course (CS231n).
Stars: β 249 (-33.42%)
Fft Conv PytorchImplementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
Stars: β 65 (-82.62%)
Sota CvA repository of state-of-the-art deep learning methods in computer vision
Stars: β 176 (-52.94%)
Ai PlatformAn open-source platform for automating tasks using machine learning models
Stars: β 61 (-83.69%)
Bidaf KerasBidirectional Attention Flow for Machine Comprehension implemented in Keras 2
Stars: β 60 (-83.96%)
AttentionnAll about attention in neural networks. Soft attention, attention maps, local and global attention and multi-head attention.
Stars: β 175 (-53.21%)
Cs231a NotesThe course notes for Stanford's CS231A course on computer vision
Stars: β 230 (-38.5%)
Deep Kernel GpDeep Kernel Learning. Gaussian Process Regression where the input is a neural network mapping of x that maximizes the marginal likelihood
Stars: β 58 (-84.49%)
Applying eannsA 2D Unity simulation in which cars learn to navigate themselves through different courses. The cars are steered by a feedforward neural network. The weights of the network are trained using a modified genetic algorithm.
Stars: β 1,093 (+192.25%)
ProbabilityProbabilistic reasoning and statistical analysis in TensorFlow
Stars: β 3,550 (+849.2%)
Convisualize nbVisualisations for Convolutional Neural Networks in Pytorch
Stars: β 57 (-84.76%)
Deep SpyingSpying using Smartwatch and Deep Learning
Stars: β 172 (-54.01%)
Genannsimple neural network library in ANSI C
Stars: β 1,088 (+190.91%)
Cs253.stanford.eduCS 253 Web Security course at Stanford University
Stars: β 155 (-58.56%)
DpwaDistributed Learning by Pair-Wise Averaging
Stars: β 53 (-85.83%)
JaxnetConcise deep learning for JAX
Stars: β 171 (-54.28%)
RlgraphRLgraph: Modular computation graphs for deep reinforcement learning
Stars: β 272 (-27.27%)
Mckinsey Smartcities Traffic PredictionAdventure into using multi attention recurrent neural networks for time-series (city traffic) for the 2017-11-18 McKinsey IronMan (24h non-stop) prediction challenge
Stars: β 49 (-86.9%)
NeuralLATEX: TikZ package for drawing neural networks. Also available on CTAN at http://www.ctan.org/tex-archive/graphics/pgf/contrib/neuralnetwork
Stars: β 169 (-54.81%)
TensorhubTensorHub is a library built on top of TensorFlow 2.0 to provide simple, modular and repeatable abstractions to accelerate deep learning research.
Stars: β 48 (-87.17%)
Cs193p Fall 2017These are the lectures, slides, reading assignments, and problem sets for the Developing Apps for iOS 11 with Swift 4 CS193p course offered at the Stanford School of Engineering and available on iTunes U.
Stars: β 141 (-62.3%)
Ml In TfGet started with Machine Learning in TensorFlow with a selection of good reads and implemented examples!
Stars: β 45 (-87.97%)
Awesome Ml Model CompressionAwesome machine learning model compression research papers, tools, and learning material.
Stars: β 166 (-55.61%)
Advis.js[Tensorflow.js] AdVis: Exploring real-time Adversarial Attacks in the browser with Fast Gradient Sign Method.
Stars: β 42 (-88.77%)
CycleganTensorflow implementation of CycleGAN
Stars: β 348 (-6.95%)
YannThis toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: β 41 (-89.04%)
Cython Blisπ₯ Fast matrix-multiplication as a self-contained Python library β no system dependencies!
Stars: β 165 (-55.88%)
Journalism SyllabiComputer-Assisted Reporting and Data Journalism Syllabuses, compiled by Dan Nguyen
Stars: β 136 (-63.64%)
DapsDenoising Autoencoders for Phenotype Stratification
Stars: β 39 (-89.57%)
IresnetImproved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: β 163 (-56.42%)
Dbn CudaGPU accelerated Deep Belief Network
Stars: β 38 (-89.84%)
MonielInteractive Notation for Computational Graphs
Stars: β 272 (-27.27%)
GatGraph Attention Networks (https://arxiv.org/abs/1710.10903)
Stars: β 2,229 (+495.99%)
Tf 2.0 HacksContains my explorations of TensorFlow 2.x
Stars: β 369 (-1.34%)
N BeatsKeras/Pytorch implementation of N-BEATS: Neural basis expansion analysis for interpretable time series forecasting.
Stars: β 351 (-6.15%)
SuperviselyAI for everyone! π Neural networks, tools and a library we use in Supervisely
Stars: β 332 (-11.23%)
Neuralpde.jlPhysics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
Stars: β 295 (-21.12%)
cs229-solutions-2020Unofficial Stanford's CS229 Machine Learning Problem Solutions (summer edition 2019, 2020).
Stars: β 37 (-90.11%)
Pixel level land classificationTutorial demonstrating how to create a semantic segmentation (pixel-level classification) model to predict land cover from aerial imagery. This model can be used to identify newly developed or flooded land. Uses ground-truth labels and processed NAIP imagery provided by the Chesapeake Conservancy.
Stars: β 217 (-41.98%)
SafeSAFE: Self-Attentive Function Embeddings for binary similarity
Stars: β 112 (-70.05%)