“I am a student of computer science/engineering. How do I get into the field of machine learning/deep learning/AI?”
It’s never been easier to get started with machine learning. In addition to structured MOOCs, there is also a huge number of incredible, free resources available around the web.
Continue reading “Some Essential Hacks and Tricks for Machine Learning with Python”
I was working on a personal project on tumor detection and recognition and decided to us some image segmentation tools and techniques to refine my recognition model.
As I was working on this project, I found myself wondering—is it possible to do this on mobile? The answer is YES, and so I decided to give it a shot.
With over 2 billion active Android devices and over 1 billion active iOS users, the mobile market provides the most engaging and profitable market to build and sell new digital solutions. There are less than 4 million unique applications for each of these operating systems, with most of them performing the same or related functions.
However, the arrival of cloud-based and device-based artificial intelligence tools provides a unique opportunity to recreate the mobile experience for existing apps, as well as build entirely new mobile apps that can only be possible through the use of AI-powered tools.
Continue reading “5 App Ideas to Unleash the Power of Mobile Machine Learning”
In machine learning, overfitting is having your machine learning model study the data so well that the model somehow memorizes the data and loses the ability to predict correctly given an unseen situation.
Continue reading “Bias-Variance Tradeoff to Avoid Under/Overfitting”
In our last newsletter roundup, we looked digests for mobile development, and we covered it all: iOS, Android, React Native, and Cross-Platform. Again, my sincerest thanks to Heartbeat All-Star Zain Sajjad, whose help in putting these lists together has been invaluable.
For the last installation of our newsletter journey, let’s take a look at some of the premier newsletters for data science and analytics.
In our last newsletter roundup, we looked at the expansive landscape of AI and machine learning newsletters. Luckily for me (and Zain Sajjad, who was a huge help in putting this list together) the demarcations with mobile development newsletters are much more straightforward.
That doesn’t mean there’s any less variety or quality in the content that’s being sent all around the world every week (or every other week). I had a lot of fun researching these excellent newsletters, and I know there’s something in here that will capture your interest. So let’s jump right in!
Augmented reality (AR) is one of the fastest growing “next wave” technologies in mobile development. To define AR, I’ll turn to Jameson Toole and his post (linked below) that explores combining AR and AI in mobile development:
To help you get started with developing amazing mobile experiences with AR, we’ve compiled a helpful list of Heartbeat tutorials, explainers, and more.
As a developer, it’s crucial for your business to have access to your user’s details. Be it to monitor their usage patterns, send promotional campaigns, notify them of critical updates to your services, or for additional cross-selling of new services.
One effective technique to gather user data is via authentication. Or, put simply, a login system that lets your app know when a particular user is using the app.
Implementing a secure authentication system of this kind from the ground up might require weeks of effort, along with you having to learn a server-side framework to build the backend for the same.
Continue reading “Implementing email and password-based authentication on Android using Firebase”
This is part 3 of an ongoing series on language models, starting with defining neural machine translation and exploring the transformer model architecture, and then implementing GPT-2 from scratch.
Specifically, in the first part of the series, we implemented a transformer model from scratch, talked about language models in general, and also created a Neural Machine Translator.
A few weeks ago I looked at the speed of Core ML models running on various Apple devices. Apple’s new A12 Bionic chip paired with Core ML 2 made the latest generation of iPhones and iPads more than 10x faster than previous generations.
While faster is usually better, large differences in performance across devices make it hard for developers to keep user experience consistent. Apple’s (relatively) small product family and aggressive upgrade strategy mitigates this problem to some degree.
Continue reading “Benchmarking TensorFlow Mobile on Android devices in production”
