Image classification using batch normalization layers

One or more non-transitory computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to implement a neural network system for processing images, the neural network system comprising:

• a convolutional neural network configured to receive a network input comprising an image or image features of the image and to generate a network output for the network input, the convolutional neural network comprising:
• a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer;
• and
• a batch normalization layer between the first convolutional neural network layer and the second neural network layer, wherein the first convolutional neural network layer generates first layer outputs having a plurality of components that are indexed by feature index and spatial location index, and wherein the batch normalization layer is configured to, during training of the convolutional neural network on a batch of training examples:
• receive a respective first layer output for each training example in the batch;
• compute a plurality of normalization statistics for the batch from the first layer outputs, wherein computing a plurality of normalization statistics for the first layer outputs comprises, for each of the feature indices:
• computing a mean of the components of the first layer outputs that correspond to the feature index;
• and
• computing a variance of the components of the first layer outputs that correspond to the feature index;
• normalize each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch;
• generate a respective batch normalization layer output for each of the training examples from the normalized layer outputs;
• and
• provide the batch normalization layer outputs as input to the second neural network layer.

A method performed by one or more computers, the method comprising:

• during training of a convolutional neural network, receiving a network input comprising an image or image features of the image;
• and
• processing the network input using the convolutional neural network to generate a network output for the network input, the convolutional neural network comprising:
• a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer;
• and
• a batch normalization layer between the first convolutional neural network layer and the second neural network, wherein the first convolutional neural network layer generates first layer outputs having a plurality of components that are indexed by feature index and spatial location index, and wherein the batch normalization layer is configured to, during the training of the convolutional neural network on a batch of training examples:
• receive a respective first layer output for each training example in the batch;
• compute a plurality of normalization statistics for the batch from the first layer outputs, wherein computing a plurality of normalization statistics for the first layer outputs comprises, for each of the feature indices:
• computing a mean of the components of the first layer outputs that correspond to the feature index;
• and
• computing a variance of the components of the first layer outputs that correspond to the feature index;
• normalize each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch;
• generate a respective batch normalization layer output for each of the training examples from the normalized layer outputs;
• and
• provide the batch normalization layer outputs as input to the second neural network layer.