Skip to main content


Showing posts from December, 2021

Importance of pooling layer in CNN

I recently came across a bunch of question regarding pooling in CNN. Will removing the max pooling layer from the CNN architecture effect the accuracy? Is pooling necessary for convolutional neural network? What will happen if we remove pooling layers from the General CNN architecture? Does removing pooling layers from CNN will improve results?   There are many other similar questions like these and this article will answers all those questions. Photo by Thomas Tucker on Unsplash So, firstly if you don't know what pooling is then you can go through this article , it will help you in understanding pooling deeply. And if you just want to know the answers to the above questions then continue with this article. So, we know that pooling helps in reducing the dimension. But why we want to reduce the dimension? The answer is to reduce the computational power required to train the model. If we don't reduce the dimension then our model will take very long or most probably our machine w

How Pooling layer helps in reducing dimension in convolutional neural networks?

One of the most important layer in a CNN architecture is Pooling layer. In this article we will understand what is pooling layer? what does pooling layer do? and how pooling layer works? we will also look at different types of pooling such as max pooling, average pooling and global average pooling. Photo by Andras Kerekes What is Pooling layer and what does pooling layer do?  In simple words Pooling is used for dimensionality reduction in CNN. Why dimensionality reduction? For decreasing the computational power required to process the data. But pooling is not just for reducing the dimension only, it also helps in extracting the dominant features like edges in the image. How pooling layer works? So, now we know that pooling is used for dimensionality reduction but how pooling reduces dimension? Pooling works similar to filters. Consider the below image where we are using a filter of size 2 X 2. In case of filters, we used to multiply filter values to the input element wise and c

Onions in the stock market

   Image by  K8 Vincent Kasuga who is also known by many other names, his fans call him the Onion King, onion farmers call him a cheater, friends call him Vinny, and his wife calls him cuddlebuns, but that’s only in private. In the 1950s, cuddlebuns had a brilliant idea: what if we took shorts, but made them longer? It turned out that was called pants, and it had already been invented, but then he had another idea: he was going to corner the onion market. Now, in theory, cornering a market is simple: Step one: buy all of a commodity. Step two: stonks. Step three: profit. In practice, though, cornering a market is nearly impossible: not only would Vince need to buy almost every onion in America, he would also need to do it without anybody noticing, because if the market realized what he was up to, prices would spike before he could finish. Somehow, though, by the winter of 1955, using a combination of quiet investors, ramshackle warehouses, and the god-like high of abusing capitalism, h

How solar panel works? simply explained

 So, Most of the countries are promoting electric vehicles to reduce the pollution. But to charger those EVs we depend on power plants and most of them use coal to generate electricity. So, to make EVs more environment friendly we have to look for some alternative to generate electricity. One of the environment friendly option is solar power. So lets understand how solar panel works.  Image by  Andreas G├╝cklhorn The Earth intercepts a lot of solar power:    That's ten thousand times more power than the planet's population uses. So, is it possible that one day the world could be completely reliant on solar energy? To answer that question, we first need to examine how solar panels convert solar energy to electrical energy. Solar panels are made up of smaller units called solar cells. The most common solar cells are made from silicon, a semiconductor that is the second most abundant element on Earth. In a solar cell, crystalline silicon is sandwiched between conductive layers. Eac

A simple explanation to filters, stride and padding in convolution neural networks

We know that CNN use filters to extract feature from the image. This filter moves across the image starting from top left and moving towards right. Once it reaches at the horizontal end of the image, it moves one step vertically downwards and then start moving from left to right. It repeats this process until it reaches at the lower right corner of the image. Photo by Birger Strahl Now lets see how these filters extract the features from the image, but before that lets understand what filters actually are? What are Filters? Filters are nothing but a matrix of specific number which are when multiplied by an image gives a particular feature map. For example, in the below image when multiplied by a “Right sobel” filter gives an output feature map with vertical lines detected in it. Right sobel filter on a 2d image Different filters have different specific values to detect different features. Different filter and their values Now imagine the below image as a image matrix and we pass a

Convolutional Neural Networks are easier than you think

  Photo by Kristopher Roller on Unsplash In our last article on neural networks , we learned how neural networks work. In this article we will look into another type of a neural network used in deep learning, Convolution Neural Network  also known as ConvNet/CNN. What is Convolutional neural network? A convolutional neural network is a Deep Learning  algorithm  which is designed for working with two dimensional images. It applies a filter to the input image to extract the features from the input. The same filter is applied multiple times to the input to generate a feature map which indicates the strength of the detected features. The pre processing required in a ConvNet is much lower as compared to other classification algorithms . Why CNN? Why not use simple Neural Network? To answer this question first we need to understand how convNet works. How convolutional neural networks works? Before understanding the working of convolutional neural networks let us understand how w