Machine Learning (ML)

Bayesian Belief Networks

This article covers: Prerequisite Probability concepts for Bayesian Belief Networks(BBNs), BBN components: Directed Acyclic Graph and Conditional Probability Table and implementation example in Python.

Explaining and Harnessing Adversarial examples by Ian Goodfellow

The article explains the conference paper titled "EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES" by Ian J. Goodfellow et al in a simplified and self understandable manner.

Machine Learning (ML)

Understanding ResNet50 architecture

ResNet50 is a variant of ResNet model which has 48 Convolution layers along with 1 MaxPool and 1 Average Pool layer. It has 3.8 x 10^9 Floating points operations. It is a widely used ResNet model.

Machine Learning (ML)

Value Iteration Algorithm (with a 1D example)

In this article, we have explored Value Iteration Algorithm in depth with a 1D example. This algorithm finds the optimal value function and in turn, finds the optimal policy.

Machine Learning (ML)

Applications of Principal Component Analysis (PCA)

This article gives a brief introduction to PCA and explains the applications of Principal Component Analysis in Neuroscience, Quantitative Finance, Image Compression (with a coding example), Facial Recogntion and others.

Machine Learning (ML)

One Pixel Attack for Fooling Deep Neural Networks

In this article, we have explored the paper "One Pixel Attack for Fooling Deep Neural Networks" by Jiawei Su and others which introduces a technique to modify only one pixel in an image which will lead popular models to mislabel them.

Machine Learning (ML)

Machine Learning Approach for Sentiment Analysis

The Lexical methods of Sentiment Analysis, even though easy to understand and implement, are not proven to be very accurate. Thus, we discuss the Machine Learning approach for Sentiment Analysis, focusing on using Convolutional Neural Networks for Sentiment Analysis.

Machine Learning (ML)

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images

In this article, we will have a simplified view of the research paper "Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images" by Anh

Machine Learning (ML)

Performance metrics in Classification and Regression

In this post, we will look at different performance metrics for classification and regression. For regression, metrics are Mean absolute error, Mean squared error, R-Square and many more. For classification, the metrics are accuracy, precision, recall and many more.

Machine Learning (ML)

Hindi OCR (Optical Character Recognition)

Hindi OCR is basically a model which is used to recognize handwritten Hindi (Devanagari) characters. We have demonstrated this with a custom CNN model.

Machine Learning (ML)

Understand AdaBoost and Implement it Effectively

In this article we will see how AdaBoost works and we will see main advantages and disadvantages that lead to an effective usage of the AdaBoost algorithm.

Machine Learning (ML)

Lexicon based Sentiment Analysis

Lexicon-based Sentiment Analysis techniques, as opposed to the Machine Learning techniques, are based on calculation of polarity scores given to positive and negative words in a document.

Machine Learning (ML)

Simplifying "Intriguing properties of neural networks"

In this article, we have explored the paper "Intriguing properties of neural networks" by Christian Szegedy in depth as it is an influential paper which introduces two key properties that define Neural Networks.

Machine Learning (ML)

Understanding the VGG19 Architecture

VGG19 is a variant of VGG model which in short consists of 19 layers (16 convolution layers, 3 Fully connected layer, 5 MaxPool layers and 1 SoftMax layer). There are other variants of VGG like VGG11, VGG16 and others. VGG19 has 19.6 billion FLOPs.

Machine Learning (ML)

Gaussian Naive Bayes

Gaussian Naive Bayes is a variant of Naive Bayes that follows Gaussian normal distribution and supports continuous data. We have explored the idea behind Gaussian Naive Bayes along with an example.

Machine Learning (ML)

Optical Character Recognition (OCR)

Optical Character Recognition or OCR is the technology that is used to convert characters or text that is either handwritten or printed in the form of paper into machine encoded text so that it can be saved digitally.

Machine Learning (ML)

Simplifying "Gaussian LDA for Topic Models with Word Embeddings"

In this article, we have explained the research paper titled "Gaussian LDA for Topic Models with Word Embeddings" by Rajarshi Das, Manzil Zaheer, Chris Dyer (associated with Carnegie Mellon University) in a easy fashion for beginners to get deep understanding of this paper

Machine Learning (ML)

Pachinko Allocation Model (PAM)

Pachinko Allocation Model (PAM) is a topic modeling technique which is an improvement over the shortcomings of Latent Dirichlet Allocation. In this article, we have explained it in detail.

Machine Learning (ML)

BERT for text summarization

BERT (Bidirectional tranformer) is a transformer used to overcome the limitations of RNN and other neural networks as Long term dependencies. We have explored in depth how to perform text summarization using BERT.

Machine Learning (ML)

Tensorflow.js: Machine Learning through JavaScript

Tensorflow.js is an open-source library with which we can implement machine learning in the browser with the help of JavaScript. It is powered by WebGL and provides a high-level layers API for defining models, and a low-level API for linear algebra and automatic differentiation.

Machine Learning (ML)

Convolutional Neural Network (CNN) questions

In this article, we have presented the most insightful and must attempt questions on Convolutional Neural Network (CNN) along with detailed answers so that you can understand CNN in depth.

Machine Learning (ML)

Batch Normalization

Batch normalization is a technique used to increase the stability of a neural network. It helps our neural network to work with better speed and provide more efficient results.

Machine Learning (ML)

Guide to "An embarrassingly simple approach to Zero-Shot Learning"

In this article, we have discussed about "An embarrassingly simple approach to Zero-Shot learning" and dived into details how to apply this approach that in a single line of code outperforms the state-of-art models.

Machine Learning (ML)

Types of RNN (Recurrent Neural Network)

In this article, we shall dive into Recurrent Neural Networks types after getting you briefly introduced to RNNs. In short, the different types of RNN are one to one, one to many, many to many and many to one.

Machine Learning (ML)

Understand different types of Boosting Algorithms

In this article we will dive deep into understanding Boosting and then we are going to see rapidly some derived algorithms like AdaBoost and LightGBM.