Machine learning is moving to the edge. You’ve probably read or heard this sentiment somewhere. Whether it was a WWDC session, an ARM whitepaper, or any number of insightful pieces about the future of ML, the concept of on-device machine learning is expanding in both theoretical and practical terms.
Continue reading Machine learning on mobile: What can you actually do with it?
In this article, we’re going to build a simple sentiment analysis platform using Flask, a lightweight web application framework. Our platform will be able to classify a movie review as either positive or negative. We’ll use the IMDB dataset to build a simple sentiment analysis model, save it, and host it on Heroku. We’ll use Gunicorn to serve our model.
Continue reading Build, Save, and Host Your First Machine Learning Model Using Flask and Heroku
We’ve all heard the saying A picture is worth a thousand words. But is a tarnished image with gaping holes or splotches or blurs worth a few hundred? What if you just found an age-old photograph of your grandparents’ wedding, but the surface was so worn that you could barely make out their faces. Or perhaps you got photobombed in what would otherwise have been the perfect picture. Or maybe you’re like me and are wondering why hasn’t anyone integrated an option in a smartphone camera app to remove unwanted objects from images?
The NVIDIA Jetson Nano is, essentially, an amazing little computer. I’d describe it as a lot like a Raspberry Pi, except it has a GPU.
Combine that with its low $99 USD price tag, and AI/ML enthusiasts see a cheap device that can go from desktop to edge with perfect parity.
An ideal machine for AI in the wild!
Just recently, the 5th stable version of the React Navigation library was released. Without a doubt, it’s one of the most popular navigation solutions in React Native apps that also has support for Expo.
Recently, it underwent some core changes. Specifically, how you used to define routes up until react-navigation version 4.x.x has some major changes.
Everyone knows that Swift is an open-source language from Apple and is available on macOS machines. Some of you might even know that Swift can be compiled on iPadOS.
But did you know that Swift is also available on Ubuntu? If yes, have you ever tried it?
Let’s try this out here—this post will walk you through compiling a Swift file on Ubuntu.
In this tutorial, we’re going to talk about a type of unsupervised learning model known as Boltzmann machines. We assume the reader is well-versed in machine learning and deep learning. We’ll use PyTorch to build a simple model using restricted Boltzmann machines. This model will predict whether or not a user will like a movie.
A Boltzmann machine defines a probability distribution over binary-valued patterns. What makes Boltzmann machine models different from other deep learning models is that they’re undirected and don’t have an output layer. The other key difference is that all the hidden and visible nodes are all connected with each other. Due to this interconnection, Boltzmann machines can generate data on their own. As such, it can be classified as a generative deep learning model.
Continue reading Introduction to Restricted Boltzmann Machines Using PyTorch
But there was one major issue with Prisma. It had to be run through JVM and had memory issues. The Prisma Framework is rewritten in Rust, and it addresses the issues from Prisma 1.
Prisma 1 also required a server in front of your backend server, while with the Prisma Framework, the query engine is now a bundled executable that’s run alongside the backend on the same server.
Continue reading Getting Started with the Prisma Framework (formerly Prisma 2) in React Native
In my previous article, we had a detailed discussion on the one-shot learning problem and how various algorithms tackled it in order to determine which approach was the most effective, and we settled on siamese networks. I’d encourage you to check it out:
But is this enough?Not quite! We need some hands-on-experience to actually learn how implement it. And what could be more relatable these days than facial recognition, which just happens to be a perfect use case for one-shot learning?
Continue reading One-Shot Learning (Part 2/2): Facial Recognition Using a Siamese Network
Big data and machine learning, while two separate concepts, remain interwoven in many aspects. The ability to process vast piles of data for machine learning tasks is a requirement of the field.
Apache Spark is a great framework when it comes to large-scale data processing (and has been for a while), enabling you to work with a range of big data problems. Apart from supporting cluster computing and distributivity with various languages such Java, Scala, and Python, Spark offers support for a variety of ML capabilities via its native libraries. However, its selling point remains its potential for ETL processing with large scale datasets.
Continue reading H2O AutoML + Big Data Processing with Apache Spark
