Translations:Convolutional Neural Networks/31/en - Revision history

FuzzyBot: Importing a new version from external source

2026-04-27T23:34:17Z

Importing a new version from external source

← Older revision		Revision as of 23:34, 27 April 2026
Line 1:		Line 1:
	* Use pretrained models (transfer learning) when labelled data is limited.		* Use pretrained models (transfer learning) when labelled data is limited.
	* Prefer small kernels (<math>3 \times 3</math>) stacked in depth — two <math>3 \times 3</math> layers have the same receptive field as one <math>5 \times 5</math> layer but with fewer parameters.		* Prefer small kernels (<math>3 \times 3</math>) stacked in depth — two <math>3 \times 3</math> layers have the same receptive field as one <math>5 \times 5</math> layer but with fewer parameters.
	* Apply batch normalisation after convolution and before activation.		* Apply {{Term\|batch normalization\|batch normalisation}} after convolution and before {{Term\|activation function\|activation}}.
	* Use data augmentation generously to reduce [[Overfitting and Regularization\|overfitting]].		* Use data augmentation generously to reduce [[Overfitting and Regularization\|overfitting]].
	* Replace fully connected layers with global average pooling to reduce parameters.		* Replace fully connected layers with global average {{Term\|pooling}} to reduce parameters.

FuzzyBot: Importing a new version from external source

2026-04-27T21:57:51Z

Importing a new version from external source

← Older revision		Revision as of 21:57, 27 April 2026
Line 1:		Line 1:
	* Use pretrained models (transfer learning) when labelled data is limited.		* Use pretrained models (transfer learning) when labelled data is limited.
	* Prefer small kernels (<math>3 \times 3</math>) stacked in depth — two <math>3 \times 3</math> layers have the same receptive field as one <math>5 \times 5</math> layer but with fewer parameters.		* Prefer small kernels (<math>3 \times 3</math>) stacked in depth — two <math>3 \times 3</math> layers have the same receptive field as one <math>5 \times 5</math> layer but with fewer parameters.
	* Apply ~~{{Term\|batch normalization\|~~batch normalisation}} after convolution and before ~~{{Term\|activation function\|~~activation}}.		* Apply batch normalisation after convolution and before activation.
	* Use data augmentation generously to reduce [[Overfitting and Regularization\|overfitting]].		* Use data augmentation generously to reduce [[Overfitting and Regularization\|overfitting]].
	* Replace fully connected layers with global average ~~{{Term\|~~pooling}} to reduce parameters.		* Replace fully connected layers with global average pooling to reduce parameters.

FuzzyBot: Importing a new version from external source

2026-04-27T19:41:44Z

Importing a new version from external source

← Older revision		Revision as of 19:41, 27 April 2026
Line 1:		Line 1:
	* Use pretrained models (transfer learning) when labelled data is limited.		* Use pretrained models (transfer learning) when labelled data is limited.
	* Prefer small kernels (<math>3 \times 3</math>) stacked in depth — two <math>3 \times 3</math> layers have the same receptive field as one <math>5 \times 5</math> layer but with fewer parameters.		* Prefer small kernels (<math>3 \times 3</math>) stacked in depth — two <math>3 \times 3</math> layers have the same receptive field as one <math>5 \times 5</math> layer but with fewer parameters.
	* Apply batch normalisation after convolution and before activation.		* Apply {{Term\|batch normalization\|batch normalisation}} after convolution and before {{Term\|activation function\|activation}}.
	* Use data augmentation generously to reduce [[Overfitting and Regularization\|overfitting]].		* Use data augmentation generously to reduce [[Overfitting and Regularization\|overfitting]].
	* Replace fully connected layers with global average pooling to reduce parameters.		* Replace fully connected layers with global average {{Term\|pooling}} to reduce parameters.

FuzzyBot: Importing a new version from external source

2026-04-27T00:30:27Z

Importing a new version from external source

New page

* Use pretrained models (transfer learning) when labelled data is limited.
* Prefer small kernels (<math>3 \times 3</math>) stacked in depth — two <math>3 \times 3</math> layers have the same receptive field as one <math>5 \times 5</math> layer but with fewer parameters.
* Apply batch normalisation after convolution and before activation.
* Use data augmentation generously to reduce [[Overfitting and Regularization|overfitting]].
* Replace fully connected layers with global average pooling to reduce parameters.