Question

I hope this question is simple. Please read the statement below and answer whether it is True or False. Please add some explanation as to support the answer. Thank you.

The combination of convolutional layer and pooling layer achieves partial invariance to translations in a convolutional neural network.

(TRUE / FALSE)

Answer 1

The statement is TRUE(it will be more cleared in explanation) for :

The combination of convolutional layer and pooling layer achieves partial invariance to translations in a convolutional neural network.

Explanation:-

1) A pooling layer is a new layer added after the convolutional layer. Specifically, after a nonlinearity (e.g. ReLU) has been applied to the feature maps output by a convolutional layer.They are:

1. Input Image
2. Convolutional Layer
3. Nonlinearity
4. Pooling Layer

2) The addition of a pooling layer after the convolutional layer is a common pattern used for ordering layers within a convolutional neural network that may be repeated one or more times.

3) We can get a small amount of translational invariance at each level by taking the maximum (or by averaging), a certain number of neighboring replicated detectors (convolved feature here) to give a single output to the next level. This reduces the number of inputs to the next layer of feature extraction, thus allowing us to have many more different feature maps. After several levels of pooling, however, we have lost information about the precise positions of things. This makes it impossible to use the precise spatial relationships between high-level parts for recognition. Therefore, Sometimes we can see the network architecture that only CONVOLUTIONAL LAYERS are used without POOLING LAYERS.

4) Overall, CNN is a sequence of Convolutional Layers with activation functions, and usually followed by pooling layer.