Machine Learning (ML)

Delta Rule in Neural Network

We shall be discussing Delta rule in neural networks that is used to updated weights during training a Neural Network.

Kohonen Neural Network

The Kohonen Neural Network (KNN) also known as self organizing maps is a type of unsupervised artificial neural network. This network can be used for clustering analysis and visualization of high-dimension data.

Machine Learning (ML)

Gradient Ascent

Gradient Ascent as a concept transcends machine learning. It is the reverse of Gradient Descent, another common concept used in machine learning. Gradient Ascent (resp. Descent) is an iterative optimization algorithm used for finding a local maximum (resp. minimum) of a function.

Machine Learning (ML)

Out-of-Bag Error in Random Forest [with example]

In this article, we have explored Out-of-Bag Error in Random Forest with an numeric example and sample implementation to plot Out-of-Bag Error.

Machine Learning (ML)

XNet architecture: X-Ray image segmentation

Medical image processing is an important application in Computer Vision,requires segmentation of images into body parts. Joseph Bullock and his partners in Durham University proposed a neuron network called XNet which is suitable for this task.

Machine Learning (ML)

Word Embeddings: GloVe and Word2Vec

Word Embeddings correlates the likeness of the meaning of words with their relative similarity and represent them numerically as a vector.

Machine Learning (ML)

Feature Selector Using LASSO

A technique for reducing the dimensionality of machine learning datasets is the Feature Selector. The selection process of the Feature Selector is based on a logically accurate measurement that determines the importance of each feature present in the data.

Machine Learning (ML)

Seq2seq: Encoder-Decoder Sequence to Sequence Model Explanation

In Deep learning, we all know that Recurrent Neuron Network solves time series data. Sequence to Sequence (or Seq2Seq for short) is a kind of model that was born to solve "Many to many" problem.

Machine Learning (ML)

Questions on Random Forest

In this article, we have presented the most important Interview Questions on Random Forest.

Machine Learning (ML)

Super Resolution GAN: SRGAN

Super Resolution GAN (SRGAN) is generative adversarial network that can generate high resolution images from low resolution images using perceptual loss function that is made of the adversarial loss as well as the content loss.

Machine Learning (ML)

Interview Questions on Autoencoders

In this article, we have presented most important Interview Questions on Autoencoders.

Natural Language Processing (NLP)

NLP Project: Compare Text Summarization Models

In this article, we will go over the basics of Text Summarization, the different approaches to generating automatic summaries, some of the real world applications of Text Summarization, and finally, we will compare various Text Summarization models with the help of ROUGE.

Deep Learning

Interview Questions on Transformers

The Transformers architecture introduced in the paper “Attention Is All You Need”, has changed the scenario of creating more complex and advanced NLP models. Following are the important questions for an interview on Transformers.

Machine Learning (ML)

PCA vs LDA [Differences]

This problem charged us much time, memory spaces and make difficult for our models to work with until PCA and LDA was born. In this article, we're going to discuss about how these 2 algorithms work and the differences between them.

List of Interview Questions

Interview questions on GAN

In this article, we have presented several Interview questions on Generative Adversarial Network (GAN) along with detailed answers.

Machine Learning (ML)

Huber Fitting using ADMM

Huber Fitting in general is the approach of using the Huber function to fit the data models, the advantage of this approach is due to the clever formulation of the Huber function which brilliantly combines the best features of both preceding optimization solution approaches of LAD and LS.

Machine Learning (ML)

LASSO using ADMM

LASSO is the acronym for Least Absolute Shrinkage and Selection Operator. Regression models' predictability and interpretability were enhanced with the introduction of Lasso.

Machine Learning (ML)

Least Absolute Deviation using ADMM

Least Absolute Deviation (LAD) is a powerful approach for solving optimization problems with good tolerance to outliers. Hence solving it to obtain a practicably applicable form is essential to take advantage of its theoretical prowess.

Machine Learning (ML)

Sentiment Analysis with Naive Bayes Classifier Built from Scratch

In this article, we will implement a Naive Bayes classifier from scratch to perform sentiment analysis.

Machine Learning (ML)

ADMM - Alternating Direction Method of Multipliers

Distributed convex optimization, and in particular, large-scale issues occurring in statistics, machine learning, and related fields, are particularly suited to the Alternating Direction Method of Multipliers (ADMM).

Machine Learning (ML)

Drone simulation with object detection

Drones are Unmanned Aerial Vehicles (UAV) that are remotely controlled either by humans or by computer programs. They range in size from under one pound to several hundred pounds.

Machine Learning (ML)

Panoptic Segmentation

Panoptic Segmentation is an improved human-like image processing approach that combines the goals of both Instance and Semantic Segmentation. It was first proposed in a 2018 paper by Alexander Kirillov.

Machine Learning (ML)

Confusion matrix and how accuracy is not the key always

Confusion matrix is a term in the field of machine learning which is generally associated with a lot of confusion on what it means, which is exactly what will be removed in this article as we understand confusion matrix.

Computer Architecture

GCC Compiler Intrinsics

In this article, we will discuss the GNU Compiler Collection (GCC), the fundamentals of intrinsics, some of the ways in which these intrinsics can speed up vector code, and we will also take a look at a list of some of the x86 intrinsics that GCC offers.

Machine Learning (ML)

Saving and Reusing Machine Learning Models

In this article, we will be learning about various ways of saving and reusing machine learning models.