Category: Other

#014 CNN Residual nets

Residual networks Last time we saw how VGG Networks work, however very deep neural networks are difficult to train because of the vanishing and exploding gradients types of problems. In this post we’ll learn about skip connections which allows us to take the activation from one layer and feed it to another layer much deeper in the neural network.  Using that we will build \(Resnets \) which enable us to train very deep networks, that…
Read more

#013 CNN VGG 16 and VGG 19

\(VGG \) neural network In the previous posts we talked about \(LeNet-5 \) and AlexNet  . Let’s now see one more example of a convolutional neural network called  \(VGG-16 \) and \(VGG-19 \) network. In this network smaller filters are used, but the network was built to be deeper than convolutional neural networks we have seen in the previous posts. Architecture of \(VGG-16 \) Remarkable thing about the \(VGG-16 \) is that instead of having so many…
Read more

#013 B CNN AlexNet

\(AlexNet \) In the previous posts we talked about LeNet−5. Let’s now see one more example of a convolutional neural network. The second convolutional neural network that we are going to present is \(AlexNet \) neural network. An input to this neural network is \(227\times227\times3\). We have a color image as an input and that is why we have \(3 \) channels. \(AlexNet \) architecture Let’s explore the architecture of this convolutional neural network. \(Conv\enspace1\) First,…
Read more

#013 A CNN LeNet-5

\(LeNet-5 \) The goal of \(LeNet-5 \) was to recognize handwritten digits. So, it takes as an input \(32\times32\times1 \) image. It is a grayscale image, thus the number of channels is \(1 \). Here is a picture of it’s arhitecture.  \(LeNet-5 \) architecture In the first step we use \(6\enspace5 \times 5\) filters with a stride \(s=1 \) and \(no\enspace padding\). Therefore we end up with a \(28 \times 28 \times 6 \) volume.…
Read more

#012 CNN Convolutional Neural Networks – An Overview

Last time we saw we are Convolutions very useful when we include them in our neural networks. In this post we will give just an overview of the 11 Convolutional Neural Network architectures.   Convolutional Neural Netwok Academic Paper Authors Python experiments    LeNet-5  ” Gradient-based Learning Applied to Document Recognition “ Yann LeChun, Leon Bottou, Youshua Bengaio, Patric Haffner    AlexNet  “ImageNet Classification with Deep Convolutional Neural Networks” Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton  …
Read more