A function that increases or decreases rapidly at first, but then steadily slows as time moves, can be called a logarithmic function.
For example, we can say that the number of cases of the ongoing COVID-19 pandemic follows a logarithmic pattern, as the number of cases increased very fast in the beginning and are now slowing a bit.
Continue reading A Comprehensive Guide To Logarithmic Regression
Swift Packages are one of the most exciting applications of the Swift programming language. Packages allow for development beyond your usual app — it even works on Linux!
It’s well-known that projects without documentation don’t get the attention they deserve. And rightfully so, because it’s very hard for new “users” (developers who consume your package) to get started with your project if documentation is lacking. However, writing and maintaining documentation is often seen as a boring task. Besides, your documentation will quickly be outdated if you don’t update it.
Continue reading Generating docs for your Swift Package and hosting on GitHub Pages
In deep learning, one of the most widely-used technologies is TensorFlow, an end-to-end open-source platform for building models. It has a vast, flexible ecosystem of tools, libraries, and community resources. With the power of TensorFlow, researchers and developers can develop and deploy ML-powered applications.
In this tutorial, we’re going to work with TensorFlow.js, TensorFlow’s JavaScript library. We’ll use this library to learn to perform object detection—and specifically, detect instances of people—using our device’s webcam. The idea is fairly simple. We launch the camera in observation mode. Then, when it detects a human, it starts to record the movement of the person until the person is no longer in the view of the camera.
Continue reading Getting Started with Object Detection Using TensorFlow.js
For this tutorial, you need a basic knowledge of React Native and some familiarity with Expo. You’ll also need the Expo client installed on your mobile device or a compatible simulator installed on your computer Instructions on how to do this can be found here.
Continue reading Handling responsive layouts in React Native apps
We’ve seen a bunch of great use cases for on-device ML, but sometimes it’s easy for us to get a bit lost in the weeds. For many mobile developers, the idea of machine learning can sound scary—math, a steep learning curve, and questions about the need for machine learning features in the first place.
Mobile apps are made of screens that can vary in number depending on the app you’re developing. Handling user navigation can be tricky to learn and implement in mobile apps, but with dedicated open source libraries like react-navigation, the process becomes a lot easier.
React Navigation is a common library among React Native developers. It’s built with JavaScript, and you can create React components and apply any navigation pattern. On the device, it’ll provide a natural look and feel.
Continue reading How Authentication Flow works in React Native apps using React Navigation 4.x
Photography has been Apple’s central focus since the inception of the iPhone. Over the years, they’ve released amazing new features that make the world a difficult place to live in without an iPhone. Users are able to capture better and better photos, thanks to state-of-the-art image intelligence features Apple has steadily added.
Specifically, Apple has been investing heavily in the field of computer vision, rolling out major updates every year through its Vision framework, which was released in 2017.
Continue reading Scanning Credit Cards with Computer Vision on iOS
Nowadays, one issue that flies under the radar for Android developers is app security. Although the Android OS possesses a layer of security that’s sufficient most of the time, it can be enhanced by adding an extra layer of security using some advanced mechanisms and features.
Today’s article is going to cover some of these best practices and mechanisms to better secure your apps.
Continue reading Securing Network and Inter-App Communications on Android
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
