Network in Network Deep Neural Network Explained with Pytorch
Network in Network (NiN) is a very influential paper that introduced two massively useful concepts to the next generation of deep neural network architecture.
Namely, 1x1 convolution throughout the network and global average pooling for the classification layer.
Table of Content
Introduction: 0:00
1x1 convolution: 0:49
Global Average Pooling: 2:33
Datasets: 3:22
Results: 3:43
Code: 6:07
Conclusion: 8:59
Paper:
📌 https://arxiv.org/pdf/1312.4400
Code used in this video:
📌 https://github.com/yangqiongyongyu/Ne...
Abstract:
"We propose a novel deep network structure called "Network In Network" (NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. Instead, we build micro neural networks with more complex structures to abstract the data within the receptive field. We instantiate the micro neural network with a multilayer perceptron, which is a potent function approximator. The feature maps are obtained by sliding the micro networks over the input in a similar manner as CNN; they are then fed into the next layer. Deep NIN can be implemented by stacking mutiple of the above described structure. With enhanced local modeling via the micro network, we are able to utilize global average pooling over feature maps in the classification layer, which is easier to interpret and less prone to overfitting than traditional fully connected layers. We demonstrated the state-of-the-art classification performances with NIN on CIFAR-10 and CIFAR-100, and reasonable performances on SVHN and MNIST datasets. "
----
Join the Discord for general discussion: / discord
----
Follow Me Online Here:
Twitter: / yacineaxya
GitHub: https://github.com/yacineMahdid
LinkedIn: / yacinemahdid
___
Have a great week! 👋