TensorFlow.js is an extremely powerful machine learning framework. But its demonstration apps can be a little intimidating for newcomers. I wanted to make a straightforward example of a model that demonstrates the basics of TensorFlow.js. In this article walks through a simple classification model which solves for XOR.
A recent project I worked on involved a thermal camera. At first it wasn’t clear whether or not we would be able to wire it into a web app. I decided to create a few alternative prototypes to fall back on, one of which involved motion detection. Anything moving is likely to produce heat. The effect works by capturing two frames, 3 seconds apart, from the live video feed. Even someone holding still to pose for the camera moves a little. Cheating, for sure, but the effect works really well.
As part of the Skippy Yippee campaign I was tasked to create a web app which simulates drawing in peanut butter. In addition to a website, the campaign was set to have a duplicate experience inside of a banner ad as well as a mobile ad. HTML5 canvas was the clear choice as it was most… Read the full article
During development of Turkey Volume Guessing App, it began to crash at random on the iPad 2. Being a Phonegap app, it was the age old problem of memory limits in Mobile Safari. In this case the app is generating three large uncompressed png images which must be stored for use at different points in… Read the full article
With the Chrome and Firefox teams making clear plans to deprecate Flash, the de-facto banner ad standard, there has been a frantic push to convert Flash ads to HTML5 format. HTML5 can replicate most of the features of Flash, but is often more complicated and time consuming to produce. I’ve spent a lot of time… Read the full article