Author archives

CNN

CNN stands for convolutional neural network. It is mostly used for developed for object recognition tasks such as handwritten digit recognition. There are four types of layers in a Convolutional Neural Network: 1. Convolutional Layers. 2. Pooling Layers. 3. Fully-Connected Layers. 4.Dropout layers. CNN is just a function which operates on another function in the below …

Naive Bayes

The Naive Bayes Classifier technique is based on the so-called Bayesian theorem and is particularly suited when the dimensionality of the inputs is high. Naive Bayes is a classi cation algorithm for binary and multiclass classi cation problems. The technique is easiest to understand when described using binary or categorical input values. It is called naive Bayes or …

Filters in Image Processing

Filters in image processing are used to smooth or sharpen the images, there are mainly two classes of filters Low Pass Filters and High Pass Filters. In Low pass filters process blocks the high-frequency pixel and allows low-intensity values or frequency to pass through it. In High pass filter process blocks the low-frequency pixels and …

Morphological Operation

Morphology is a branch in which we study the shape and size of an object or in other words, we may say we find the structure of the object. We use the concept of structuring element in this. So what is Structuring Element?. Structuring Elements is a mask or window which is placed on the original image …

Edge Detection

An Edge is a boundary between two regions having different intensity level. When an image change from black to white or vice versa we get an edge. Edge detection is very useful in detecting discontinuity of an image. There are different types of edges in an image like Step Edges, Ramp Edges, Ridge Edges. In image processing, …

Gradient Descent

Gradient Descent Gradient Descent is an optimization algorithm that optimize the cost of the function.The goal is to continue to try different values for the coefficients, evaluate their cost and select new coefficients that have a slightly better (lower) cost. https://www.hackerearth.com/blog/machine-learning/3-types-gradient-descent-algorithms-small-large-data-sets/ https://medium.com/@zhaoyi0113/python-implementation-of-batch-gradient-descent-379fa19eb428 https://www.analyticsvidhya.com/blog/2017/03/introduction-to-gradient-descent-algorithm-along-its-variants/