The past year of learning ushered in a variety of new experiences for instructors and students alike, and the United States Military Academy at West Point was no exception. In addition to masks in the classroom, reduced class sizes to allow for social distancing, rigorous testing and tracing efforts, and precautionary remote video classes, we have also needed to adjust aspects of our teaching styles. While such adjustments were voluntary, to enhance the discussion I chose to teach several lessons outside under large white tents and even in stadium bleachers to safely enable larger conversations with my cadets. Sometimes this meant carrying a large whiteboard with a tripod out to the stadium. At other times it meant putting quiz-style questions on a website so that students could submit answers via forms that were easier to grade while allowing everyone to work at a safe distance on individual devices.
Today’s handheld devices are powerful enough to run neural networks locally without the need for a cloud server connection, which can be a great convenience when you’re on the go. Deploying and running a custom neural network on your phone or tablet is not straightforward, though, and the process depends on the operating system of the machine. In this post, I will focus on iOS devices and walk you through all the necessary steps to train a custom image classifier neural network model using the Wolfram Language, export it through ONNX (new in Version 12.2), convert it to Core ML (Apple’s machine learning framework for iOS apps) and finally deploy it to your iPhone or iPad.
Cars are getting smarter and more connected, yet how much have you explored the technology that helps run our vehicles? I was curious to see how I could connect to my vehicle’s communication center and what kind of interface I could create in Wolfram Notebooks to report on the data gathered.
Explore the contents of this article with a free Wolfram System Modeler trial. Wolfram System Modeler 12.2 was just released, featuring things such as personalization of plots, new model libraries and extended GUI support for advanced modeling. One of the other additions is a new workflow for generating 3D models from 3D shapes. We will use this feature to illustrate some bizarre and counterintuitive physics.
Ever since Thomas Robert Malthus’s book An Essay on the Principle of Population, scientists have sought to determine the limit to the growth of human population due to finite resources. One such resource is groundwater. About 40% of global food production ultimately depends on irrigation and, increasingly, the source of irrigation water is groundwater aquifers. Groundwater irrigation allows farmers to increase crop yields, maintain them in dry spells and overcome temporal mismatches between growing seasons and seasonal rain. In many parts of the world, groundwater withdrawal (or pumping from wells) exceeds recharge, leading to groundwater depletion. In these regions, the “lifespan” of groundwater aquifers is limited, putting a bound on the amount of irrigation per year and the sustainability of groundwater-based agriculture. The goal of this study was to propose a dynamical systems framework capable of explaining past trends in groundwater-based irrigation and providing forecasts of food production.
In early October, by what at this point can only be a time-honored tradition, the Livecoding Championship returned in its fifth annual iteration as a special event during the 2020 Wolfram Technology Conference. As in preceding years, the championship offered top Wolfram Language programmers a chance to show off their knowledge, agility, typing speed and documentation-reading skills to an unfailingly adoring audience.
Students are spending countless hours online for classes this year, pushing educators to offer more engaging and worthwhile virtual content. We debuted Wolfram Daily Study Groups in early April with this in mind, and the results have far surpassed our expectations! Throughout this ongoing program, we’ve been able to keep students, professionals and lifelong learners engaged and connected in an enriching online community. With several Study Groups completed, and more in the works, we thought we’d share some of our successes so far.
Halloween this year had a surprise up its sleeve. In rare celestial serendipity, the night of costume metamorphosis also featured a full moon, which helped to conjure the spooky mood. Because it might have been the first and last full-moon Halloween that some people witnessed in their lifetime (cue ominous music), I think it was significantly underrated. Moreover, it was the day of a blue moon (the second full moon within a month), but that is not a surprise, as any Halloween’s full moon is always a blue moon. The Moon’s color did not change, though, at least for those away from the smoke of volcanos and forest fires that are capable of turning it visibly blue. To appreciate the science and uniqueness of a full moon this Halloween, I built this visualization that tells the whole story in one picture. This is how I did it.
Although this year’s Wolfram Technology Conference was virtual, that didn’t stop us from running the ninth annual One-Liner Competition, where attendees vie to produce the most amazing results they can with 128 or fewer characters of Wolfram Language code. Here are the winners, including an audio game, a hands-free 3D viewer and code that makes up countries.