Algorithms Aho Corasick Algorithm Aho Corasick algorithm is a string algorithm to find or search occurrences of k number of Patterns: P1 ,P2 .... Pk in a string text T. It is a modification over the KMP algorithm
Data Structures B+ Tree : Search, Insert and Delete operations A B+ tree is an N-ary tree with a variable often large number of children per node. A B+ tree consists of a root, internal nodes and leaves. The root may be either a leaf or a node with two or more children. It can be viewed as a B-tree in which each node contains only keys with an additional level
Machine Learning (ML) Residual Network (ResNet) ResNet makes it possible to train up to hundreds or even thousands of layers and still achieves compelling performance. Thanks to this technique they were able to train a network with 152 layers while still having lower complexity than VGGNet. It achieves a top-5 error rate of 3.57%
Machine Learning (ML) GoogleNet / InceptionNet The winner of the ILSVRC 2014 competition was GoogleNet from Google. It achieved a top-5 error rate of 6.67%. GoogleNet has 22 layer, and almost 12x less parameters (So faster and less then Alexnet and much more accurate). Their idea was to make a model that also could be used on a smart-phone
Machine Learning (ML) Architecture of AlexNet and its current use Alexnet is a Deep Convolutional Neural Network (CNN) for image classification that won the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry. We see the architecture and compare it with GoogleNet and ResNet
cyber security Distributed Denial Of Service Attack (DDoS) Distributed Denial Of Service (DDoS) is a form of cyber attack which is done to make target online services unavailable to the users. The attack disrupts the normal traffic of a targeted server, network or service by overwhelming the target or its surrounding infrastructure
cyber security Man In The Middle Attack (MitM) Man In The Middle (MitM) is a type of cyber attack in which a hacker intercepts the communication between two people either to eavesdrop or to impersonate one of the person. The aim of the attack is to steal financial details such as account details, credit card numbers or sensitive details
cyber security Denial Of Service Attack Denial Of Service Attack is a form of cyber attack basically used by hackers to prevent the victims from accessing any legitimate service. This hacker floods the web servers with excessive traffic in order to succeed in this attack. The attack does not result in theft or loss of data
cyber security SQL Injection Attack SQL(Structured Query Language) Attack is a cyber attack used for the manipulation of the backend database through the malicious SQL Query. The attack allows a hacker to cause repudiation issues and spoof the identity. The attack allows the complete exposure of the database
Data Structures B-Tree Deletion A B-tree is a tree data structure that keeps data sorted and allows searches, insertions, and deletions in logarithmic amortized time. Deletion in a B Tree is similar to insertion. At first the node from which a value is to be deleted is searched. If found out, then the value is deleted.
Data Structures B-Tree : Searching and Insertion A B-tree is a self-balanced search tree data structure that keeps data sorted and allows searches, insertions, and deletions in logarithmic amortized time. Unlike self-balancing binary search trees, it is optimized for systems that read and write large blocks of data like database and file systems
Machine Learning (ML) Floating point operations per second (FLOPS) of Machine Learning models In this article, we take a look at the FLOPs values of various machine learning models like VGG19, VGG16, GoogleNet, ResNet18, ResNet34, ResNet50, ResNet152 and others. The FLOPS range from 19.6 billion to 0.72 billion.
Machine Learning (ML) Types of Activation Functions used in Machine Learning We explored the various types of activation functions that are used in Machine Learning including Identity function, Binary Step, Sigmoid, Tanh, ReLU, Leaky ReLU and SoftMax function. Activation function help the network use the useful information and suppress the irrelevant data points
Machine Learning (ML) Evolution of CNN Architectures: LeNet, AlexNet, ZFNet, GoogleNet, VGG and ResNet It all started with LeNet in 1998 and eventually, after nearly 15 years, lead to ground breaking models winning the ImageNet Large Scale Visual Recognition Challenge which includes AlexNet in 2012, ZFNet in 2013, GoogleNet in 2014, VGG in 2014, ResNet in 2015 to ensemble of previous models in 2016.
Data Structures Ternary Search Trees Ternary Search Tree is a special type of trie data structure and is widely used as an low memory alternative to trie in a vast range of applications like spell check and near neighbor searching. The average case time complexity is O(log N) for look-up, insertion and deletion operation.
Software Engineering Control Flow in Python In Control Flow, there are certain conditions which we put with the help of predefined syntaxes and the program then run in that order and chooses the condition as a output. Control statements include conditional and iteration statements like if else, while, do while and if elif and for loop
Machine Learning (ML) You only look once (YOLO) algorithm You only look once (YOLO) is a state-of-the-art, real-time object detection system. It is a fully convolutional network. On a Pascal Titan X, it processes images at 30 FPS and has a mAP of 57.9% on COCO. It has 75 convolutional layers with skip connections and upsampling layers and no pooling.
Machine Learning (ML) Single Shot Detection (SSD) Algorithm Single Shot MultiBox Detector (SSD) is an object detection algorithm that is a modification of the VGG16 architecture. It reached new records in terms of performance and precision for object detection tasks, scoring over 74% mAP at 59 frames per second on standard datasets such as PascalVOC and COCO
Machine Learning (ML) Overview of Object Detection in Computer Vision Object detection models are used to identify multiple relevant objects in a single image.The second significant advantage of object detection models versus image classification ones is that location of the objects is provided. Popular Object Detection Models are YOLO and SSD.
Machine Learning (ML) VGG16 architecture We have explored the VGG16 architecture in depth. VGGNet-16 consists of 16 convolutional layers and is very appealing because of its very uniform Architecture. Similar to AlexNet, it has only 3x3 convolutions, but lots of filters. It can be trained on 4 GPUs for 3 weeks.
Machine Learning (ML) Terms used in Neural Networks The common terms used in Neural Networks are Convolution, Max Pooling, Fully Connected Layer, Softmax Activation Function and Rectified Linear Units.
Machine Learning (ML) Feed Forward Neural Networks A feedforward neural network is an Artificial Neural Network in which connections between the nodes do not form a cycle. Learn about how it uses ReLU and other activation functions, perceptrons, early stopping, overfitting, and others. See the architecture of various Feed Forward Neural Networks
Machine Learning (ML) BLAS vs BLIS BLAS (Basic Linear Algebra Subprograms) and BLIS (BLAS Like Interface Software) are libraries that have revolutionized scientific computing by accelerating execution of mathematical operations on a vast range of platforms. In short, BLIS is the new generation alternative to BLAS
Python A Pythonic Way of PDF to Image Conversion Can a PDF be converted into a sequence of images through a program? If so which is the best technique to perform this conversion? This article answers the above questions.
Data Structures How many labeled and unlabeled binary tree can be there with N nodes? In this article, we see how many labeled and unlabeled binary trees we can have with N nodes. This is related to the Catalan Numbers. Binary Tree : A tree whose elements have 0 or 1 or 2 children is called a binary tree.
