Machine Learning (ML)

3D U-Net Volumetric Segmentation

In this article, we have explored 3D U-Net model which is an enhancement of 2D U-Net model and is used for Volumetric Segmentation applications.

Gaussian Error Linear Unit (GELU)

In this article, we will talk about a relatively new activation function and somewhat better as well. Basically we will be discussing about Gaussian Error Linear Unit or GeLU.

Machine Learning (ML)

kn2row / kn2col Convolution

In this article, we will cover 2 different convolution methods: Kn2row and Kn2col Convolution which are alternatives to Im2row and Im2col. Kn2row and Kn2col are space efficient variants.

Machine Learning (ML)

Swish Activation Function

In this article, we have explored Swish Activation Function in depth. This was developed by Researchers at Google as an alternative to Rectified Linear Unit (ReLu).

Machine Learning (ML)

Project on Reconstructing Face using PCA

In this article, we have demonstrated a project "face" where we find the set of faces when combined, resulting in face of person A. We do this using Machine Learning techniques like Principal Component Analysis, Face Reconstruction and much more.

Machine Learning (ML)

SSD Model Architecture

SSD has been defined as “a method for detecting objects in images using a single deep neural network”. But before we get into that let us first understand what object detection means.

Machine Learning (ML)

Exponential Linear Unit (ELU)

Exponential Linear Unit (ELU) is an activation function which is an improved to ReLU. We have explored ELU in depth along with pseudocode.

Machine Learning (ML)

Im2row Convolution

In this article, we will understand about Im2row Convolution which is an approach to perform Convolution by modifying the layout of image and filter. It is a better alternative to Im2col.

Machine Learning (ML)

U-Net architecture

In this article, we have explained U-Net architecture along with other key ideas like Downsampling and Upsampling path with features and applications of U-Net.

Machine Learning (ML)

Linear Activation Function

In this article, we have explored Linear Activation Function which is one of the simplest Activation function that can be used Neural Networks.

Machine Learning (ML)

Filter and Channel Pruning

In this article, we will cover the idea of Pruning which is an important optimization technique for CNN models. It reduces the size of models as well as the Inference time. We dive into two main types of Pruning that is Channel Pruning and Filter Pruning.

Machine Learning (ML)

Bellman's Optimality Equation

In this article, we will be walking through the concept behind Bellman's Optimality equation, and how it is used in the case of Reinforcement Learning.

Machine Learning (ML)

Binary Step Function

Binary step function is one of the most common activation function in neural networks out there. But before we get into it let's take a look at what activation functions and neural networks are.

Machine Learning (ML)

Different types of CNN models

In this article, we will discover various CNN (Convolutional Neural Network) models, it's architecture as well as its uses. Go through the list of CNN models.

Machine Learning (ML)

Augmented Random Search (ARS)

Augmented random search (ARS)is a model-free reinforcement learning, and a modified basic random search (BRS) algorithm, the algorithm was first published in 2018 by the trio - Horia Mania, Aurelia Guy, and Benjamin Recht from the University of California, Berkeley.

Machine Learning (ML)

Squeeze and Excitation (SE) Network

This article describes what are Convolutional Neural Network and What are Squeeze and Excitation blocks.

Machine Learning (ML)

Sigmoid Activation (logistic) in Neural Networks

In this article, we will understand What are Sigmoid Activation Functions? And What are it’s Advantages and Disadvantages?

Machine Learning (ML)

Object Detection ML Application

In this article, we have explained one of the most popular applications of Machine Learning namely Object Detection. We have explained the input, output, models used and evaluation metrics for Object Detection.

Machine Learning (ML)

Best First Search algorithm

Best First Search is a searching algorithm which works on a set of defined rules. It makes use of the concept of priority queues and heuristic search. The objective of this algorithm is to reach the goal state or final state from an initial state by the shortest route possible.

Machine Learning (ML)

A * Search Algorithm

In this article, we are going to have a look at the A * Search Algorithm , its properties, some of its advantages and disadvantages as well as real life applications.

Machine Learning (ML)

Dying ReLU Problem

In this article, we will understand What is ReLU? and What do we mean by “Dying ReLU Problem” and what causes it along with measures to solve the problem.

Machine Learning (ML)

Types of Dimensionality Reduction Techniques

In this article, we will learn Why is Dimensionality Reduction important and 5 different Types of Dimensionality Reduction Techniques like Principal Component Analysis, Missing Value Ratio, Random Forest, Backward Elimination and Forward Selection.

Machine Learning (ML)

The ShuffleNet Series (Part 3): Implementation using Pytorch

We have covered every step involved in training and testing our ShuffleNet model that performs multi-class image classification. The introduction of the CIFAR 10 dataset and result discussion are also included.

Machine Learning (ML)

Precision, Recall, Sensitivity and Specificity

In this article, we have explained 4 core concepts which are used to evaluate accuracy of techniques namely Precision, Recall, Sensitivity and Specificity. We have explained this with examples.

Deep Learning

ShuffleNet Series (Part 2): A Comparison with Popular CNN architectures

This article covers the comparison of ShuffleNet with some famous architectures. It also covers how well the newer variants of ShuffleNet are as compared to their older counterparts.