| _ | relu | _ |
|---|
| Approximating | relu | Networks by Single-Spike Computation |
| AutoReP: Automatic | relu | Replacement for Fast Private Network Inference |
| Blues: Before- | relu | -estimates Bayesian Inference for Crowd Counting |
| Depth Selection for Deep | relu | Nets in Feature Extraction and Generalization |
| Driver Mental Fatigue Detection Based on Head Posture Using New Modified | relu | -BiLSTM Deep Neural Network |
| Dynamic | relu | |
| Global-connected network with generalized | relu | activation |
| If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on | relu | networks |
| L* | relu | : Piece-wise Linear Activation Functions for Deep Fine-grained Visual Categorization |
| Lightweight | relu | -Based Feature Fusion for Aerial Scene Classification, A |
| PEA: Improving the Performance of | relu | Networks for Free by Using Progressive Ensemble Activations |
| Randomized Gradient-Free Attack on | relu | Networks, A |
| Refinement and Universal Approximation via Sparsely Connected | relu | Convolution Nets |
| Rethinking | relu | to Train Better CNNs |
| Total contribution score and fuzzy entropy based two-stage selection of FC, | relu | and inverseReLU features of multiple convolution neural networks for erythrocytes detection |
| Why | relu | Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem |
16 for relu