Xception: Deep Learning with Depthwise Separable Convolutions_1649843991900.pdf
ZONEOUT : REGULARIZING RNNS BY RANDOMLY PRESERVING HIDDEN ACTIVATIONS_1649843992123.pdf
VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION_1649843991247.pdf
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks_1649843991379.pdf
Weighted Residuals for Very Deep Networks_1649843991563.pdf
Wide Residual Networks_1649843991678.pdf
UNDERSTANDING LOCALLY COMPETITIVE NETWORKS_1649843989927.pdf
Understanding data augmentation for classification: when to warp?_1649843990591.pdf
Understanding intermediate layers using linear classifier probes_1649843990825.pdf
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition_1649843988332.pdf
Training Very Deep Networks_1649843989323.pdf
STRIVING FOR SIMPLICITY : THE ALL CONVOLUTIONAL NET_1649843986723.pdf
Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning_1649843987277.pdf
Swapout: Learning an ensemble of deep architectures_1649843987500.pdf
Residual Networks of Residual Networks: Multilevel Residual Networks_1649843985984.pdf
Rethinking the Inception Architecture for Computer Vision_1649843986209.pdf
Noisy Activation Functions_1649843984915.pdf
On the Computational Efficiency of Training Neural Networks_1649843985144.pdf
RESNET IN RESNET : GENERALIZING RESIDUAL ARCHITECTURES_1649843985348.pdf
Residual Networks are Exponential Ensembles of Relatively Shallow Networks_1649843985555.pdf
Learning Multiple Layers of Features from Tiny Images_1649843984084.pdf
Multi-Residual Networks_1649843984529.pdf
Network In Network_1649843984753.pdf
ImageNet Large Scale Visual Recognition Challenge_1649843982428.pdf
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning_1649843983353.pdf
Layer Normalization_1649843983656.pdf
Going deeper with convolutions_1649843981020.pdf
Gradual DropIn of Layers to Train Very Deep Neural Networks_1649843981233.pdf
Identity Mappings in Deep Residual Networks_1649843981399.pdf
ImageNet Classification with Deep Convolutional Neural Networks_1649843981646.pdf
Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?_1649843979674.pdf
Dropout: A Simple Way to Prevent Neural Networks from Overfitting_1649843980374.pdf
FRACTAL NET : ULTRA-DEEP NEURAL NETWORKS WITHOUT RESIDUALS_1649843980629.pdf
Deeply-Fused Nets_1649843978970.pdf
Densely Connected Convolutional Networks_1649843979198.pdf
Deep Pyramidal Residual Networks_1649843978325.pdf
Deep Residual Learning for Image Recognition_1649843978760.pdf
Data Programming: Creating Large Training Sets, Quickly_1649843977007.pdf
Decision Forests, Convolutional Networks and the Models in-Between_1649843977258.pdf
Deconstructing the Ladder Network Architecture_1649843977554.pdf
Deep Learning Made Easier by Linear Transformations in Perceptrons_1649843977697.pdf
Deep Networks with Stochastic Depth_1649843977920.pdf
Convolutional Neural Fabrics_1649843976147.pdf
Convolutional Residual Memory Networks_1649843976477.pdf
DEEP CONVOLUTIONAL NEURAL NETWORK DESIGN PATTERNS_1649843976802.pdf
Caffe: Convolutional Architecture for Fast Feature Embedding ∗_1649843975043.pdf
Competitive Multi-scale Convolution_1649843975566.pdf
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift_1649843974122.pdf
Bilinear CNNs for Fine-grained Visual Recognition_1649843974541.pdf