• TensorFlow

  • Referenced in 401 articles [sw15170]
  • purposes of conducting machine learning and deep neural networks research, but the system is general...
  • PyTorch

  • Referenced in 236 articles [sw20939]
  • strong GPU acceleration. PyTorch is a deep learning framework that puts Python first...
  • Keras

  • Referenced in 128 articles [sw15491]
  • Keras: Deep Learning library for Theano and TensorFlow. Keras is a minimalist, highly modular neural ... Keras if you need a deep learning library that: allows for easy and fast prototyping...
  • darch

  • Referenced in 270 articles [sw11086]
  • publications ”A fast learning algorithm for deep belief nets” (G. E. Hinton, S. Osindero...
  • DGM

  • Referenced in 54 articles [sw39282]
  • deep learning algorithm for solving partial differential equations. High-dimensional PDEs have been a longstanding ... PDEs by approximating the solution with a deep neural network which is trained to satisfy ... Bellman PDE and Burgers’ equation. The deep learning algorithm approximates the general solution ... dimensional space). We call the algorithm a “Deep Galerkin method (DGM)” since it is similar...
  • Caffe

  • Referenced in 60 articles [sw17850]
  • Caffe is a deep learning framework made with expression, speed, and modularity in mind...
  • MXNet

  • Referenced in 32 articles [sw20940]
  • MXNet is a deep learning framework designed for both efficiency and flexibility. It allows ... MXNet is also more than a deep learning project. It is also a collection ... blue prints and guidelines for building deep learning systems, and interesting insights of DL systems...
  • DeepWalk

  • Referenced in 39 articles [sw39604]
  • modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs. DeepWalk...
  • Tensor2Tensor

  • Referenced in 25 articles [sw26507]
  • short, is a library of deep learning models and datasets designed to make deep learning...
  • PDE-Net

  • Referenced in 31 articles [sw36963]
  • paper, we present an initial attempt to learn evolution PDEs from data. Inspired ... development of neural network designs in deep learning, we propose a new feed-forward deep ... proposed PDE-Net is to learn differential operators by learning convolution kernels (filters), and apply...
  • AlexNet

  • Referenced in 343 articles [sw38522]
  • convolutional neural network that is 8 layers deep. You can load a pretrained version ... animals. As a result, the network has learned rich feature representations for a wide range ... more pretrained networks in MATLAB®, see Pretrained Deep Neural Networks...
  • STL-10 dataset

  • Referenced in 22 articles [sw39164]
  • recognition dataset for developing unsupervised feature learning, deep learning, self-taught learning algorithms...
  • PointNet

  • Referenced in 27 articles [sw31209]
  • PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Point cloud...
  • torchdiffeq

  • Referenced in 24 articles [sw35082]
  • usage of ODE solvers in deep learning applications, see [1]. As the solvers are implemented...
  • cuDNN

  • Referenced in 11 articles [sw17848]
  • cuDNN: Efficient Primitives for Deep Learning. We present a library of efficient implementations of deep ... learning primitives. Deep learning workloads are computationally intensive, and optimizing their kernels is difficult ... there is no analogous library for deep learning. Without such a library, researchers implementing deep ... BLAS, with optimized routines for deep learning workloads. Our implementation contains routines for GPUs, although...
  • FaceNet

  • Referenced in 21 articles [sw21626]
  • present a system, called FaceNet, that directly learns a mapping from face images ... feature vectors. Our method uses a deep convolutional network trained to directly optimize the embedding ... intermediate bottleneck layer as in previous deep learning approaches. To train, we use triplets...
  • DeepLab

  • Referenced in 20 articles [sw15303]
  • task of semantic image segmentation with Deep Learning and make three main contributions that ... which feature responses are computed within Deep Convolutional Neural Networks. It also allows...
  • Edward

  • Referenced in 14 articles [sw21517]
  • models on small data sets to complex deep probabilistic models on large data sets. Edward ... three fields: Bayesian statistics and machine learning, deep learning, and probabilistic programming...
  • Chainer

  • Referenced in 13 articles [sw26707]
  • next-generation open source framework for deep learning. Chainer is a Python-based deep learning...
  • OverFeat

  • Referenced in 17 articles [sw17857]
  • ConvNet. We also introduce a novel deep learning approach to localization by learning to predict...