Category: Articles

Generative adversarial networks (GANs) are among the more significant advancements in deep learning in recent years. Previously, we used machine learning and deep learning techniques with a considerable amount of data to build a model to understand data by classifying them. But now, with GANs, we use an algorithm that generates data for us.

Two of the most commonly used and efficient generative models are Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN).

Continue reading Generative Adversarial Networks (GANs) for Mobile Devices

At some point, you might have asked yourself, What are the origins of parameters for artificial neural networks? What is the purpose of the weight? What if no bias is used?

In this tutorial, we set out to answer those questions by working from the most simple artificial neural network (ANN), to something much more complex. Let’s start by building a machine learning model with no parameters—which is Y=X.

Continue reading ­­From Y=X to Building a Complete Artificial Neural Network

In the landscape of new technologies that are capable of revolutionizing our daily lives, few are as tantalizing as facial recognition technologies. With all the recent controversy around Clearview AI, people are paying more and more attention to the technology, and they’re also eager to understand the how the tech works, and it’s limitations. This article won’t cover this ethical issue, but I’ll try my hand at explaining some facial recognition and detection techniques.

Continue reading Face Recognition and Detection on iOS Using Native Swift Code, Core ML, and ARKit

In a recent blog post, Facebook announced React Native version 0.62, and one of the top features of this release was a default integration of Flipper.

Flipper is an open source mobile debugging platform backed by Facebook. It is widely used by Android & iOS developers. Flipper’s simple and intuitive interface helps developers to visualise, inspect & control apps. It aims to be the number one companion for mobile app development.

Continue reading Flipper: React Native App Debugging

Deep learning has seen tremendous progress over the past few years. This is largely due to the emergence of deep learning frameworks such as PyTorch and TensorFlow, which have greatly simplified even the most sophisticated research.

With smartphones having become the devices we use the most, the next wave of innovation is going to center on how we can leverage these rapid advances in deep learning to enhance our smartphone experiences. AI-powered mobile applications will become (and already are) smart enough to understand us and help us perform tasks via visual perception, language understanding, and voice recognition, even when not connected to the internet.

Continue reading PyTorch Mobile: Image classification on Android

In a previous article, I discussed the possibilities of computer vision-based deep learning with both RNNs and CNNs.

Generally, ML engineers will specialize in one model architecture and let the other slide.

My point and purpose for writing this post is the following: learning both allows to tackle a wider range of use-cases.

Continue reading Recurrent Neural Networks (RNNs) in Computer Vision: Image Captioning

Linear regression is an algorithm that finds a linear relationship between a dependent variable and one or more independent variables. The dependent variable is also called label and independent variables are called features as well.

Linear regression is one of the most foundational algorithms for statistical and machine learning analysis.

PyTorch is an open source machine learning framework introduced by Facebook in 2016. PyTorch is based on the Torch library, and it’s a Python-based framework as well. Apart from its Python interface, PyTorch also has a C++ front end.

Continue reading Linear Regression with PyTorch and Python

Matplotlib is the most popular data visualization library in Python. It allows us to create figures and plots, and makes it very easy to produce static raster or vector files without the need for any GUIs.

This tutorial is intended to help you get up-and-running with Matplotlib quickly. We’ll go over how to create the most commonly used plots, and discuss when to use each one.

Continue reading Introduction to Matplotlib — Data Visualization in Python

The quality of images is relevant in building compression and image enhancement algorithms. Image Quality Assessment (IQA) is divided into two main areas; reference-based evaluation and no-reference evaluation.

Reference-based methods rely on high-quality images to evaluate the difference between two images. Structural Similarity Index is one example of a reference-based method. Unlike reference-based methods, however, no-reference methods don’t require a base image for evaluating the quality of an image. These methods just receive an image whose quality is being assessed.

Continue reading Research Guide: Image Quality Assessment for Deep Learning

Pruning is a technique in deep learning that aids in the development of smaller and more efficient neural networks. It’s a model optimization technique that involves eliminating unnecessary values in the weight tensor. This results in compressed neural networks that run faster, reducing the computational cost involved in training the networks. This is even more crucial when deploying models to mobile phones or other edge devices. In this guide, we’ll look at some of the research papers in the field of pruning neural networks.

Continue reading Research Guide: Pruning Techniques for Neural Networks