Machine Learning (ML)

Understanding Recurrent Neural Networks with an example of assigning an emoji to a sentence

In this article, we explored the basic ideas of Recurrent Neural Networks with an example to assign an emoji to a sentence based on the emotion

Understanding Convolutional Neural Networks through Image Classification

In this article, we explored the ideas involved in Convolutional Neural Networks (CNN) through Image Classification

Machine Learning (ML)

Feature detection as in 1999: SIFT explained with Python implementation

SIFT (Scale Invariant Feature Transform) is a feature detection algorithm in computer vision to detect and describe local features in images designed in 1999

Machine Learning (ML)

Document Clustering using K Means

In this article, we use ideas from TF IDF and similarity metrics to use K Means clustering algorithm to cluster documents.

Natural Language Processing (NLP)

Find similarity between documents using TF IDF

We will follow NLP techniques like TF IDF to achieve document similarity in this article. Did you know that even today 4 out of 5 systems use NLP techniques to deal with document similarity?

Machine Learning (ML)

Face detection as done in 2001: Viola Jones Algorithm

Viola Jones algorithm is one face detection algorithm which was in use back in 2001 when such applications where not so cool

Machine Learning (ML)

Ensemble methods in Machine Learning: Bagging, Boosting and Stacking

We will see what an ensemble method is, why they are trendy, and what are the different types of ensemble methods and how to implement these methods using scikit-learn and mlxtend in Python.

Machine Learning (ML)

Image to Image Translation using CycleGANs with Keras implementation

Want to know how to generate Monet style paintings from any photograph of any scenery around the world? Enter CycleGANs. Read on to know more about CycleGANs and how they can be used in Image-to-Image Translation.

Machine Learning (ML)

Importance of Loss Function in Machine Learning

A loss function is a measure of how good your prediction model does in terms of being able to predict the expected outcome(or value).

Machine Learning (ML)

Face Aging using Conditional GANs with Keras implementation

Felt intrigued when the FaceApp generated realistic photos of you at an older age? Read on to know how conditional GANs can be used for face aging, and how to implement it on your own using Keras!

Machine Learning (ML)

Basics of Image Classification Techniques in Machine Learning

You will get n idea about What is Image Classification?, pipeline of an image classification task including data preprocessing techniques, performance of different Machine Learning techniques like Artificial Neural Network, CNN, K nearest neighbor, Decision tree and Support Vector Machines

Machine Learning (ML)

Converting colored images (RGB) to grayscale using Autoencoder

We built an autoencoder from scratch in TensorFlow to generate the grayscale images from colored images.

Machine Learning (ML)

Understanding Support Vector Machines (SVMs) in depth

Support vector machines (SVMs) are a particularly powerful and flexible class of supervised algorithms for both classification and regression.

Machine Learning (ML)

Generate new MNIST digits using Autoencoder

In this article, we will learn how autoencoders can be used to generate the popular MNIST dataset and we can use the result to enhance the original dataset.

Machine Learning (ML)

Understanding Deep Convolutional GANs with a PyTorch implementation

In this article, we will briefly describe how GANs work, what are some of their use cases, then go on to a modification of GANs, called Deep Convolutional GANs and see how they are implemented using the PyTorch framework.

Machine Learning (ML)

Data Analysis using Regression

In this article, we have clarified the most usually utilized kinds of regressions in information science and its application in data analysis

Machine Learning (ML)

Using Histogram of Oriented Gradients (HOG) for Object Detection

Principle behind histogram of oriented gradients is that local object appearance and shape within an image can be described by the distribution of intensity gradients or edge directions and hence, can be used for object detection

Machine Learning (ML)

Learn about various Object Detection Techniques

We will understand what is object detection, why we need to do object detection and the basic idea behind various techniques used to solved this problem. We start with the basic techniques like Viola Jones face detector to some of the advanced techniques like Single Shot Detector.

Machine Learning (ML)

Build and use an Image Denoising Autoencoder model in Keras

In this article, we will see How encoder and decoder part of autoencoder are reverse of each other? and How can we remove noise from image, i.e. Image denoising, using autoencoder? in Keras

Machine Learning (ML)

Understand Stacked Generalization (blending) in depth with code demonstration

Basic idea behind stacking is to combine the predictions of 2 or more models to get predictions of higher accuracy than the previous submodels. We demonstrate the idea using a code example

Machine Learning (ML)

Image Denoising and various image processing techniques for it

We will take a look at what is an Image?, what is an Image Noise?, what are the various types of Noise?. Following it, we will understand the various traditional image processing filters and techniques used for image denoising.

Machine Learning (ML)

Use of deep learning in NLP techniques

You will get an idea about What is NLP?, use of deep learning in NLP and 5 impressive applications of deep learning for NLP like image captioning

Machine Learning (ML)

Applications of Autoencoders

Autoencoders are neural networks that aim to copy their inputs to outputs. The applications of autoencoders are Dimensionality Reduction, Image Compression, Image Denoising, Feature Extraction, Image generation, Sequence to sequence prediction and Recommendation system.

Machine Learning (ML)

Different types of Autoencoders

Autoencoder is an artificial neural network used to learn efficient data codings in an unsupervised manner. There are 7 types of autoencoders, namely, Denoising autoencoder, Sparse Autoencoder, Deep Autoencoder, Contractive Autoencoder, Undercomplete, Convolutional and Variational Autoencoder.

Machine Learning (ML)

Whitening with PCA with code demonstration

When we are training our model on images, the raw input is quite redundant because the pixels that are adjacent to each other are highly correlated. The goal of Whitening is to reduce redundancy in these images by making features less correlated to each other and same variance