Convolutional Neural Networks
AlexNet
Introduced by Krizhevsky et al. in ImageNet Classification with Deep Convolutional Neural NetworksAlexNet is a classic convolutional neural network architecture. It consists of convolutions, max pooling and dense layers as the basic building blocks. Grouped convolutions are used in order to fit the model across two GPUs.
Source: ImageNet Classification with Deep Convolutional Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| General Classification | 51 | 13.93% |
| Quantization | 37 | 10.11% |
| Image Classification | 31 | 8.47% |
| Classification | 23 | 6.28% |
| Object Detection | 22 | 6.01% |
| Object Recognition | 19 | 5.19% |
| Model Compression | 12 | 3.28% |
| Network Pruning | 8 | 2.19% |
| Semantic Segmentation | 6 | 1.64% |
Convolution
Dense Connections
Dropout
Grouped Convolution
Local Response Normalization
Max Pooling
ReLU
Softmax
