Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Normalizacija po sloju (Batch Normalization)× | ResNet (rezidualna mreža)× | |
|---|---|---|
| Područje | Duboko učenje | Duboko učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 2015 | 2016 |
| Tvorac≠ | Ioffe, S. & Szegedy, C. | He, K.; Zhang, X.; Ren, S.; Sun, J. |
| Vrsta≠ | Normalization technique (applied per mini-batch during training) | Deep Convolutional Neural Network with skip connections |
| Temeljni izvor≠ | Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), PMLR 37, 448–456. link ↗ | He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. DOI ↗ |
| Drugi nazivi≠ | BatchNorm, BN, batch norm, mini-batch normalization | ResNet, Residual Network, Deep Residual Learning, ResNet-50 |
| Srodne≠ | 1 | 4 |
| Sažetak≠ | Batch Normalization is a training technique introduced by Sergey Ioffe and Christian Szegedy in 2015 that normalizes the pre-activation outputs of each layer using the mean and variance computed over the current mini-batch. By stabilizing the input distribution to each layer throughout training, it substantially reduces internal covariate shift, enabling the use of higher learning rates and making deep networks train faster and more reliably. | ResNet (Residual Network) is a deep convolutional neural network architecture introduced by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun at CVPR 2016. By inserting shortcut (skip) connections that carry the input of a block directly to its output — defining the block's task as learning a residual correction rather than a full mapping — ResNet enabled training of networks with hundreds or even thousands of layers without the vanishing-gradient degradation that had previously made very deep networks impractical. It won the ILSVRC 2015 image recognition competition with a top-5 error of 3.57% and remains the most widely used backbone architecture in computer vision. |
| ScholarGateSkup podataka ↗ |
|
|