$wagm@nia's repositories
Empowering-Journalists
We believe that curbing this subset of fake news would involve providing the necessary tools to journalists and users who take the time to sift through trustworthy content. In this light, our solution is to devise a methodology and program to assist a journalist to identify if an image and associated title are trustworthy. The fundamentals of our approach are based on corroboration of news, i.e, the image must be used in credible news websites with text similar to that of the associated title for the image and text to be reliable. If not, we recommend that the journalist (or user) perform a human verification procedure.
Backpropagation_implementation
This repo. implements the backpropagtion algorithm widely used in Machine Learning. The user inputs the number of hidden neurons while the algorithm trains the Neural Network on the created model and the training dataset. Finally, the the machine predicts the outcomes on the testing dataset and plots the associated loss.
CNN_Chars74k
Implementing variations of Convolutional Neural Networks using the Chars74k dataset.
Computer-Vision-Basics
Fundamental tutorials to understand the basics of Image Processing and Computer Vision
DeliveryCab
A basic delivery driver game that includes simple game mechanics—boosts, bumps & collisions.
Examining-Adversarial-Attacks-on-Image-Classification-Models
Current research on adversarial examples is largely focussed on deriving general defences against these attacks for all ML models irrespective of their architecture. In contrast to this methodology, we believe that each network architecture needs to be examined separately in order to make effective and specialized defensive capabilities. We must analyze the robustness of each architecture in isolation against different types of adversarial examples to understand the extent to which they are susceptible. Therefore, In this paper, we examine the extent to which Variational Auto-Encoders (Convolutional and Vanilla) and Convolutional Neural Networks (CNNs) are vulnerable to several gradient-based attacks on two types of datasets — high pixel density (Labelled Faces in the Wild dataset) and low pixel density (MNIST). Our aim is to review the confidence of each attack, its validity and hence, the degree of effectiveness of the attack taking place for both types of architectures. Additionally, we also examine the role siamese networks could potentially play in creating more secure and robust systems.
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
HTML101-Business-Card
A simple digital business card created during Scrimba's HTML & CSS course
HTML101-Company-Website
A simple company website made post the Scrimba HTML & CSS course
HTML101-GIFt-Site
A simple site full of GIFs on hover made during Scrimba's HTML & CSS course
HTML101-Google-Clone
A simple static HTML & CSS Google Homepage Clone made during Scrimba's course
HTML101-Hometown-Site
A basic site about Bengaluru for the finalproject of Scrimba's HTML & CSS course
HTML101-Personal-Site
A basic personal site with restricted information made during Scrimba's html & css course
Javascript-101
All projects developed to learn the basics of Javascript through Scrimba.
JS101-Bball-Scoreboard
A simple basketball scoreboard with functionality made during Scrimba's JS course
JS101-Blackjack-Game
A simple version of the blackjack game made during Scrimba's JS course
JS101-Chrome-Extension
A simple chrome extension for lead tracking made during Scrimba's JS course
JS101-Emoji-Fighter
Basic random emoji selector game using JS made during Scrimba's JS course
JS101-Password-Generator
A random password generator created during Scrimba's JS course
JS101-Unit-Converter
A simple unit converter made during Scrimba's Javascript basics course
Neural-Network-From-Scratch
Implementing an Artificial Neural Network based on Adrej Karpathy's Micrograd
Polynomial_Estimator
This repo. contains the code to create polynomial estimators, additionally,
React101-Business-Card
A business card made in React
React101-React-Facts
A static page made using React during the Scrimba React course
Simple-Django-App
This is a simple Django app to test Model-Views-Templates structures as well as url mapping.
Simple_Blog
A simple blog created on Django
Simply_CRUD_App_Django
Trying out a few CRUD operations and template/model views.