Core ML was released in June at WWDC 2017. They “introduc[ed] machine learning frameworks just for you guys to enable all the awesome things.” In the announcement, they promised image recognition, word prediction in keyboards, showing pictures of only red flowers all happening directly on the device. So 8 months later, what awesome things are we doing with Core ML and AI on mobile devices?
Continue reading “The Coming Wave of AI-Enabled Apps — GitHub Edition”
I recently had a friend text me and say, “Andrew, I’ve been getting a ton of matches on Tinder, but I still haven’t been able to find the one. I think it’s because I’m not using enough linear algebra. Can you help me out?”
And I replied, “Wow, that’s a weirdly specific question. This sounds like a fake situation. But yes, of course, I’ll see what I can do.” In this article, we’ll set out to help my friend find the one. But how?
Continue reading “The Key to Finding The One on Tinder? Vectors & Machine Learning”
It’s great that you’re thinking of building your own machine learning-powered mobile app — but there are some key considerations to keep in mind. This article will discuss three things that can keep you on-track to quickly, efficiently, and effectively building your app.
Continue reading “3 Tips for Building your First Mobile Machine Learning App”
In our review of object detection papers, we looked at several solutions, including Mask R-CNN. The model classifies and localizes objects using bounding boxes. It also classifies each pixel into a set of categories.
Therefore, it also produces a segmentation mask for each Region of Interest. In this piece, we’ll work through an implementation of Mask R-CNN in Python for image segmentation.
As a developer who grew up playing Pokémon, the projects I do for fun usually have to do with Pokémon. The dataset is just too fun to work with, and you feel like you’re a child again while you’re building the thing (whatever it might be).
In this tutorial, we’ll create a chatbot version of the Pokédex. We’ll use React Native to build the app and Dialogflow to build the brains of the chatbot.
Continue reading “Creating a “Pokédex” Chatbot with React Native and Dialogflow”
Anscombe’s quartet demonstrates a very significant idea: we need to visualize data before analyzing it. The quartet consists of four hypothetical datasets each containing eleven data points.
Whereas all these datasets have essentially the same descriptive statistics including the mean, variance, correlation, and regression line, they have very different distributions when graphed.
Continue reading “Analyzing Machine Learning Models with Yellowbrick”
In terms of usefulness and popularity, object detection is arguably at the forefront of the computer vision domain. A diverse application of CV with many facets, object detection helps solve some of the most explored problems—face detection, and more recently, pose estimation, hand/gesture tracking, AR filters, and so on.
Data augmentation involves the process of creating new data points by manipulating the original data. For example, for images, this can be done by rotating, resizing, cropping, and more.
This process increases the diversity of the data available for training models in deep learning without having to actually collect new data. This then, generally speaking, improves the performance of deep learning models.
Continue reading “Research Guide: Data Augmentation for Deep Learning”
For a healthcare research project I’m working on, I’m investigating for a federated learning platform that supports mobile and wearable platforms—in particular on the Apple ecosystem.
Federated learning represents a tremendous opportunity for the adoption of machine learning in many use cases, and especially where efficiency and privacy concerns require us to distribute the training process, instead of centrally collecting data on the cloud and applying traditional ML pipelines.
In a previous article, we reviewed some of the pre-eminent literature on pruning neural networks. We learned that pruning is a model optimization technique that involves eliminating unnecessary values in the weight tensor. This results in smaller models with accuracy very close to the baseline model.
In this article, we’ll work through an example as we apply pruning and view the effect on the final model size and prediction errors.
Continue reading “Pruning Machine Learning Models in TensorFlow”
