# Convolutional Neural Networks

Tutorial overview with detailed visualizations of the **evolution of convolutional neural networks up to the state-of-art**. Find it here

### Index

1: LeNet - LeCun - 1998 Paper (TBI)

2: AlexNet - Krizhevsky - 2012 Paper

3: GoogLeNet (Inception) - Szegedy - 2014 Paper (TBI)

4: VGG - Simonyan / Zisserman - 2014 Paper (TBI)

5: ResNets - He - 2015 Paper

- Tutorial on Residual Deep Convolutional Networks (Demistifying ResNet Paper)

- Tutorial on modifying the ResNet for CIFAR-10

- PyTorch Implementation Explanation

- Code for ResNets on CIFAR10

6: DenseNets - Huang - 2016 - Paper

- Tutorial on Residual Deep Convolutional Networks (Demistifying ResNet Paper)

- Tutorial on modifying the DenseNet for CIFAR-10

- Code for DenseNets on CIFAR10

7: MobileNets - Howard - 2016 Paper (TBI)

8: FractalNets - Larsson - 2016 Paper (TBI)

## Convolutional Operations

The intention is to make familiar with how I use to represent those operations in the rest of the works on this blog to ease the visualization of such operations.

I encourage you to check out the quick read of this post to feel more confortable on more difficult topics like VGG, ResNets or DenseNets

## ResNets - Residual Learning

In this work I go through the original paper explaining with nice visualizations how every operation is performed. Check the post here .

Then, I follow that documentation to explained the Official PyTorch Implementation and understand how it is built on python using PyTorch.

Finally, I make another tutorial explaning what modifications are requiered to adjust the ResNet to work on CIFAR10 dataset, since the paper and the PyTorch implementation focus on ImageNet dataset.

The code to build DenseNets for CIFAR10 matching the parameters reported at the paper can be found here

## DenseNets - Residual Learning

In this work I go through the original paper explaining with nice visualizations how every operation is performed. Check the post here .

Then, I follow the notation on the Official PyTorch Implementation to adjust it to CIFAR10. I made another post explaining these modifications required for CIFAR10 since the paper and the PyTorch implementation focus on ImageNet dataset.

The code to build DenseNets for CIFAR10 matching the parameters reported at the paper can be found here