October 2016
Intermediate to advanced
654 pages
22h 41m
English
| Name | Layers | Top-5 Error (%) | References |
| AlexNet | 8 | 15.3 | Krizhevsky et al. (2012) |
| VGG Net | 19 | 7.3 | Simonyan and Zisserman (2014) |
| ResNet | 152 | 3.6 | He et al. (2016) |

When an image is filtered, the output is another image that contains the filter’s response at each spatial location, e.g., one with its edges emphasized. We could also think of such an image as a feature map that indicates where certain features were detected in the image—e.g., edges. However, in a deep network the initial filtered images or feature maps are subjected to many further levels of filtering. Over many successive ...
Read now
Unlock full access