Machine Learning Archives

Deep Learning, Machine Learning, TensorFlow

How to Program Generative Adversarial Network with Tensorflow 2.0

Posted on April 27, 2021 by Sandeep Kumar

This guide is a hands-on tutorial to program a generative adversarial network with TensorFlow 2.0 to generate new data using the past data. We need to train two networks, Generator, and Discriminator, using alternative approach where for each batch, we train the discriminator first such that it iden...

Deep Learning, Machine Learning, TensorFlow, Uncategorized

Step-by-Step Guide to Build CNN Model with Tensorflow

Posted on April 24, 2021 by Sandeep Kumar

This tutorial is a step-by-step guide to create, train and evaluate a CNN Model with TensorFlow. Mainly there are 3 approaches to define a convolutional neural network with TensorFlow. The best way to become comfortable to define a CNN at the end of this post is to try each step yourself while going...

Deep Learning, Machine Learning

How Does Variational Autoencoder Work? Explained!

Posted on April 19, 2021 by Sandeep Kumar

Variational Autoencoder is a an explicit type generative model which is used to generate new sample data using past data. VAEs do a mapping between latent variables, dominate to explain the training data and underlying distribution of the training data. These latent variables vectors can be used to ...

Deep Learning, Machine Learning

Basics of Generative Adversarial Network Model

Posted on April 10, 2021 by Sandeep Kumar

Generative Adversarial Network a.k.a GANs is a generative model which is used to generate new samples using training data. The output samples are similar to the training data but not exactly the same as our goal is to generate more diverse data from what we already have. Goal of GANs The distributio...

ANN, Artificial Intelligence, Deep Learning, Machine Learning

Comparison of Sigmoid, Tanh and ReLU Activation Functions

Posted on August 19, 2020 by Divyang Goswami

Introduction In Artificial Neural network (ANN), activation functions are the most informative ingredient of Deep Learning which is fundamentally used for to determine the output of the deep learning models. In this blog, we will discuss the working of the ANN and different types of the Activat...

Machine Learning

8 Important Evaluation Metrics for Classification Models

Posted on March 26, 2020 by Sandeep Kumar

This post explains important evaluation metrics to check while measuring the performance of a classification model. These are Accuracy, Precision, Recall, Sensitivity, Specificity, False Positive Rate, False Negative Rate, and F1 Score. We’ll cover one by one each metric by calculating its value u...

Machine Learning

Understand Confusion Matrix Using Real-life Classification Example

Posted on March 25, 2020 by Sandeep Kumar

First I’d like to explain what is the use of a confusion matrix. Classification Problems are solved using Supervised Machine learning algorithms. In these problems, our goal is to categories an object using its features. For e.g, Identify a fruit using its taste, color and size or check out ...

Machine Learning

Explain Echelon Form of a Matrix

Posted on February 26, 2020 by Sandeep Kumar

Echelon Form of a matrix is used to solve a linear equation by converting a complex matrix to a simple matrix. A matrix is in an Echelon Form if it satisfies some conditions which we’ll discuss in this post. We must know how to convert a matrix into Echelon Form and simplify our matrix for [&h...

Machine Learning

Working of Bagging and Boosting in Ensemble Learning

Posted on February 10, 2020 by Surbhi Arora

Bagging and Boosting both are Ensemble Learning techniques. Ensemble Methods are an important addition to Data Scientists toolbox. Here, weak learners combined together to become strong learners. And offers better performance than an individual one. What is an Ensemble Method The main logic behind t...

Machine Learning

What is the difference between Variance and Bias in Machine Learning?

Posted on February 8, 2020 by Surbhi Arora

From the perspective of Supervised Machine Learning, we know all models have errors. We need to minimize the error so as to make the model useful. For this, we need to minimize two major sources of error- Bias and Variance. What is Bias? The tendency of the algorithm to learn wrong details from the ...

1 2 3