• TensorFlow

  • Referenced in 327 articles [sw15170]
  • purposes of conducting machine learning and deep neural networks research, but the system is general...
  • darch

  • Referenced in 262 articles [sw11086]
  • package is for generating neural networks with many layers (deep architectures) and train them with ... publications ”A fast learning algorithm for deep belief nets” (G. E. Hinton, S. Osindero ... Reducing the dimensionality of data with neural networks” (G. E. Hinton, R. R. Salakhutdinov). This...
  • PyTorch

  • Referenced in 170 articles [sw20939]
  • Dynamic neural networks in Python with strong GPU acceleration. PyTorch is a deep learning framework...
  • BinaryConnect

  • Referenced in 14 articles [sw35871]
  • BinaryConnect: Training Deep Neural Networks with binary weights during propagations. Deep Neural Networks (DNN) have ... research and development of dedicated hardware for Deep Learning (DL). Binary weights, i.e., weights which ... components of the digital implementation of neural networks. We introduce BinaryConnect, a method which consists...
  • DeepFace

  • Referenced in 17 articles [sw21625]
  • face representation from a nine-layer deep neural network. This deep network involves more than...
  • Keras

  • Referenced in 105 articles [sw15491]
  • Deep Learning library for Theano and TensorFlow. Keras is a minimalist, highly modular neural networks ... research. Use Keras if you need a deep learning library that: allows for easy...
  • BinaryNet

  • Referenced in 10 articles [sw35872]
  • Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained...
  • Reluplex

  • Referenced in 7 articles [sw31367]
  • Efficient SMT Solver for Verifying Deep Neural Networks. Deep neural networks have emerged ... efficient technique for verifying properties of deep neural networks (or providing counter-examples). The technique ... neural networks. The verification procedure tackles neural networks as a whole, without making any simplifying ... evaluated our technique on a prototype deep neural network implementation of the next-generation airborne...
  • SSD

  • Referenced in 12 articles [sw26652]
  • objects in images using a single deep neural network. Our approach, named SSD, discretizes...
  • PDE-Net

  • Referenced in 25 articles [sw36963]
  • latest development of neural network designs in deep learning, we propose a new feed-forward ... deep network, called PDE-Net, to fulfill two objectives at the same time: to accurately ... learning convolution kernels (filters), and apply neural networks or other machine learning methods to approximate...
  • DeepLab

  • Referenced in 15 articles [sw15303]
  • feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively...
  • DeepFool

  • Referenced in 5 articles [sw20937]
  • simple and accurate method to fool deep neural networks. State-of-the-art deep neural ... robustness of state-of-the-art deep classifiers to such perturbations on large-scale datasets ... efficiently compute perturbations that fool deep networks, and thus reliably quantify the robustness of these ... simple and accurate method to fool deep neural networks...
  • SGDR

  • Referenced in 8 articles [sw30752]
  • improve its anytime performance when training deep neural networks. We empirically study its performance...
  • SqueezeNet

  • Referenced in 8 articles [sw30749]
  • model size. Recent research on deep neural networks has focused primarily on improving accuracy...
  • DeepPPI

  • Referenced in 4 articles [sw30745]
  • Prediction of Protein-Protein Interactions with Deep Neural Networks. The complex language of eukaryotic gene ... using a recent machine learning advance-deep neural networks (DNNs). We aim at improving ... propose a method called DeepPPI (Deep neural networks for Protein-Protein Interactions prediction), which employs ... deep neural networks to learn effectively the representations of proteins from common protein descriptors...
  • SegNet

  • Referenced in 14 articles [sw27575]
  • present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise...
  • NICE

  • Referenced in 5 articles [sw29631]
  • building blocks, each based on a deep neural network. The training criterion is simply...
  • DeepTracker

  • Referenced in 3 articles [sw25889]
  • Visualizing the Training Process of Convolutional Neural Networks. Deep convolutional neural networks (CNNs) have achieved ... other state-of-the-art ”very deep” CNN models...
  • SchNetPack

  • Referenced in 3 articles [sw25772]
  • development and application of deep neural networks to the prediction of potential energy surfaces ... contains basic building blocks of atomistic neural networks, manages their training and provides simple access ... atomcentered symmetry functions and the deep tensor neural network SchNet as well as ready ... PyTorch deep learning framework, SchNetPack allows to efficiently apply the neural networks to large datasets...
  • Marabou

  • Referenced in 2 articles [sw31368]
  • Framework for Verification and Analysis of Deep Neural Networks. Deep neural networks are revolutionizing ... pressing need for tools and techniques for network analysis and certification. To help in addressing ... present Marabou, a framework for verifying deep neural networks. Marabou is an SMT-based tool...