Machine Learning tutorial

Major ideas in Creating Realistic Talking Head Models from Photo

The only issue in creating artificial videos is that they require a large amount of training data, however, we might want it to learn from only a few image views of a person. This is the concern of this paper.

machine learning

AVX512 VNNI: This instruction boosts ML performance by 2X

AVX512 Vector Neural Network Instructions (AVX512 VNNI) is an x86 extension Instruction set and is a part of the AVX-512 ISA. It is designed to accelerate convolutional neural network for INT8 inference

machine learning

Polynomial regression using scikit-learn

In this article, we have implemented polynomial regression in python using scikit-learn and created a real demo and get insights from the results.

machine learning

Learn to use TPOT: An AutoML Tool

TPOT stands for Tree Base Pipeline Optimization Tool. It is used to solve or give a idea on machine learning problems. It helps us to explore some of pipeline confiuration that we did not consider earlier for our model.

machine learning

Exploratory Data Analysis using Python

In this article, we will see what Exploratory Data Analysis (EDA) is, what are the different steps in it, and further how to implement it using Python

machine learning

Edmundson Heuristic Method for text summarization

Edmundson Heuristic Method proposes the use of a subjectively weighted combination of features as opposed to traditionally used feature weights generated using a corpus

machine learning

Applying Naive Bayes classifier on TF-IDF Vectorized Matrix

We will use Naive Bayes classifier on IF-IDF vectorized matrix for text classification task. We use the ImDb Movies Reviews Dataset for this.

machine learning

Hopfield Network

Hopfield Network is a recurrent neural network with bipolar threshold neurons. It consists of a set of interconnected neurons that update their activation values asynchronously.

machine learning

Luhn’s Heuristic Method for text summarization

The idea of Luhn’s Heuristic Method for text summarization is that any sentence with maximum occurrences of the highest frequency words(Stopwords) and least occurrences are not important to the meaning of the document

machine learning

Eigenfaces for Face recognition

In this article, we have explored EigenFaces in depth and how it can be used for Face recognition and developed a Python demo using OpenCV for it.

machine learning

KL Sum algorithm for text summarization

Kullback-Lieber (KL) Sum algorithm for text summarization which focuses on minimization of summary vocabulary by checking the divergence from the input vocabulary.

machine learning

Image Recognition using Transfer Learning Approach

In this post, we will explore Transfer Learning and see what exactly it is and how it works along with a Python implementation for the image recognition tasks.

machine learning

LBPH algorithm for Face Recognition

In this article, we will explore the Local Binary Patterns Histogram algorithm (LBPH) for face recognition. It is based on local binary operator and is one of the best performing texture descriptor.

machine learning

Face Recognition using Fisherfaces

In this article, we will explore FisherFaces techniques of Face Recognition. FisherFaces is an improvement over EigenFaces and uses Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA).

machine learning

Latent Semantic Analysis for text summarization

Latent Semantic Analysis is an efficient technique for text summarization in order to abstract out the hidden context of the document.

machine learning

Random Forests using Scikit-learn

In this article, we will implement random forest in Python using Scikit-learn (sklearn). Random forest is an ensemble learning algorithm which means it uses many algorithms together

machine learning

Decision Trees using Scikit-learn

In this article, we will understand decision tree by implementing an example in Python using the Sklearn package (Scikit Learn).

machine learning

SumBasic algorithm for text summarization

SumBasic is an algorithm to generate multi-document text summaries. Basic idea is to utilize frequently occuring words in a document than the less frequent words so as to generate a summary

machine learning

Deep Q-Learning: Combining Deep Learning and Q-Learning

The idea in deep Q networks is that the states and possible outcomes in Q-Learning is replaced with a neural network which tries to approximate Q Values. It is referred to as the approximator

machine learning

SMOTE for Imbalanced Dataset

In this post, we will see how to deal with an imbalanced dataset using SMOTE (Synthetic Minority Over-sampling TEchnique). We will also see its implementation in Python.

machine learning

Object Detection using Region-based Convolutional Neural Networks (R-CNN)

In this post, we will look at Region-based Convolutional Neural Networks (R-CNN) and how it used for object detection. We'll see why the R-CNN came into the picture when CNNs were already into existence.

machine learning

Text Summarization Techniques

Text Summarization is the process of creating a compact yet accurate summary of text documents. In this article, we will cover the different text summarization techniques.

machine learning

Text Preprocessing Techniques

In this post, we will look at a variety of text preprocessing techniques which are frequently used for a Natural language processing (NLP) task.

software engineering

MLIR: Redefining the compiler infrastructure

MLIR (Multi-level intermediate representation) is an intermediate representation system between a language or library and the compiler backend (like LLVM)

machine learning

Intuitive Introduction to Gaussian Processes

Gaussian Process is a non-parametric model that can be used to represent a distribution over functions.