Machine learning: Lenet-5 Architecture

Lenet-5 is one of the easiest pre-trained models proposed by Yann Lecun in the year 1998.

The network has 5 layers with learnable parameters and hence named Lenet-5. It has three sets of convolution layers with a combination of average pooling. After convolution and average pooling layers, we have two fully connected layers. At last, a Softmax classifier which classifies the images into respective class.

The input to this model is a 32x32 grayscale image hence the number of channel is one.

We then apply the first convolution operation with the filter size 5x5 and we have 6 such filters. As result we get a feature map of size 28x28x6. Here the number of channels is equal to the number of filter applied.

After the first pooling operation, we apply the average pooling and the size of the feature map is reduced by half. Note that, the number of channels is intact.

Next, we have a convolution layer with sixteen filters of size 5x5. Again the feature map changed it is 10x10x16. The output size is calculated in a similar manner. After this, we again applied an average pooling or subsampling layer, which again reduce the size of the feature map by half i.e 5x5x16.

Then we have a final convolution layer of size 5x5 with 120 filters. As shown in the above mage. Leaving the feature map size 1x1x120. After which flatten result is 120 values.

After these convolution layers, we have a fully connected layer with eighty-four neurons. At last, we have an output layer with ten neurons since the data have ten classes.

Here is the final architecture of the Lenet-5 model.