Ideas in Machine Learning have a "winner takes all" quality. When an idea takes off, it dominates the field so completely that one tends to believe it is the only idea worth pursuing. Today, Deep ...
Batch Normalization in Deep Networks
In this post, we will learn what is Batch Normalization, why it is needed, how it works, and how to implement it using Keras. Batch Normalization was first introduced by two researchers at Google, ...
Understanding AlexNet
Billionaire investor and entrepreneur Peter Thiel's favorite contrarian questions is What important truth do very few people agree with you on? If you had asked this question to Prof. Geoffrey ...
Number of Parameters and Tensor Sizes in a Convolutional Neural Network (CNN)
In this post, we share some formulas for calculating the sizes of tensors (images) and the number of parameters in a layer in a Convolutional Neural Network (CNN). This post does not define basic ...
Feature Based Image Alignment using OpenCV (C++/Python)
In this post, we will learn how to perform feature-based image alignment using OpenCV. We will share code in both C++ and Python. We will demonstrate the steps by way of an example in which we will ...
Principal Component Analysis
In this post, we will learn about Principal Component Analysis (PCA) -- a popular dimensionality reduction technique in Machine Learning. Our goal is to form an intuitive understanding of ...