• SqueezeNet

  • Referenced in 21 articles [sw30749]
  • offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed ... training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud ... autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware...
  • CNTK

  • Referenced in 9 articles [sw21056]
  • popular model types such as feed-forward DNNs, convolutional nets (CNNs), and recurrent networks (RNNs/LSTMs...
  • dnner

  • Referenced in 7 articles [sw38982]
  • Python library dnner - DNNs Entropy from Replicas. The code in this package computes the entropy...
  • lsd

  • Referenced in 7 articles [sw39754]
  • installation of the dedicated package dnner (DNNs Entropy from Replicas...
  • DeepPINK

  • Referenced in 3 articles [sw42244]
  • facilitate the interpretability of deep neural networks (DNNs), existing methods are susceptible to noise ... increase the interpretability and reproducibility of DNNs by incorporating the idea of feature selection with...
  • GXNOR-Net

  • Referenced in 2 articles [sw32923]
  • unified discretization framework. Although deep neural networks (DNNs) are being a revolutionary power to open ... operations, make the on-chip training of DNNs quite promising. Therefore there is a pressing ... implementing the back propagation algorithm on discrete DNNs. While for the second issue, we propose ... weights and activations become ternary values, the DNNs can be reduced to sparse binary networks...
  • DeepPPI

  • Referenced in 4 articles [sw30745]
  • recent machine learning advance-deep neural networks (DNNs). We aim at improving the performance...
  • OpenSALICON

  • Referenced in 2 articles [sw25869]
  • power of high-level semantics encoded in DNNs pretrained for object recognition. Two key components ... fine-tuning the DNNs with an objective function based on the saliency evaluation metrics ... tracking benchmark datasets. Results demonstrate that our DNNs can automatically learn features for saliency prediction...
  • NeST

  • Referenced in 2 articles [sw31716]
  • grow-and-prune paradigm. Deep neural networks (DNNs) have begun to have a pervasive impact ... automate the generation of compact and accurate DNNs. NeST starts with a randomly initialized sparse ... that NeST yields accurate, yet very compact DNNs, with a wide range of seed architecture...
  • NNV

  • Referenced in 3 articles [sw32539]
  • based verification framework for deep neural networks (DNNs) and learning-enabled cyber-physical systems...
  • Rx-Caffe

  • Referenced in 1 article [sw25898]
  • Networks on Resistive Crossbars. Deep Neural Networks (DNNs) are widely used to perform machine learning ... high computation and storage demands of DNNs have led to a need for energy-efficient ... resistance, sneak paths, and interconnect parasitics. Although DNNs are somewhat tolerant to errors in their ... context of large-scale DNNs with 2.6-15.5 billion synaptic connections. In this work...
  • NATTACK

  • Referenced in 1 article [sw32886]
  • construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper ... attack algorithm that can defeat both vanilla DNNs and those generated by various defense techniques ... according to the testing against 2 vanilla DNNs and 13 defended ones, it outperforms state ... examples are not as transferable across defended DNNs as them across vanilla DNNs...
  • SyReNN

  • Referenced in 1 article [sw40543]
  • analyzing deep neural networks. Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety ... important domains. Formally, DNNs are complicated vector-valued functions which come in a variety ... sizes and applications. Unfortunately, modern DNNs have been shown to be vulnerable to a variety ... formally analyzing the properties of such DNNs. This paper introduces SyReNN, a tool for understanding...
  • PaRoT

  • Referenced in 1 article [sw31366]
  • Robust Deep NeuralNetwork Training. Deep Neural Networks (DNNs) are finding important applications in safety-critical ... assurance due to their black-box nature, DNNs pose a fundamental problem for regulatory acceptance ... robust training to be performed on arbitrary DNNs without any rewrites to the model...
  • DeepTest

  • Referenced in 1 article [sw41849]
  • Cars. Recent advances in Deep Neural Networks (DNNs) have led to the development ... their roads. However, despite their spectacular progress, DNNs, just like traditional software, often demonstrate incorrect ... potentially fatal crashes in three top performing DNNs in the Udacity self-driving car challenge...
  • daBNN

  • Referenced in 2 articles [sw31494]
  • operations in float-valued Deep Neural Networks (DNNs) with bit-wise operations. Nevertheless, there...
  • PhysNet

  • Referenced in 2 articles [sw40931]
  • scalability to large datasets, deep neural networks (DNNs) are a particularly promising ML algorithm...
  • DarkneTZ

  • Referenced in 1 article [sw32543]
  • attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices ... equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy...
  • NxTF

  • Referenced in 1 article [sw38430]
  • Intel Loihi architecture. We evaluate NxTF on DNNs trained directly on spikes as well ... models converted from traditional DNNs, processing both sparse event-based and dense frame-based data...
  • PRODeep

  • Referenced in 1 article [sw39886]
  • deep neural networks. Deep neural networks (DNNs) have been applied in safety-critical domains such ... PRODeep, a platform for robustness verification of DNNs. PRODeep incorporates constraint-based, abstraction-based...