A plane billed as the largest all-electric commercial aircraft has set a new record, taking to the skies for the first time and making a zero-emissions flight. The all-electric Cessna 208B Grand Caravan – known as the eCaravan – took off from a runway in Washington on Thursday and flew for 28 minutes, with its creators suggesting it could fill … Continue reading
Developers hoping to publish a PlayStation 4 game will have to ensure that their title also works on the upcoming PS5, according to Eurogamer. Documentation from Sony’s internal partner portal states that, as of July 13th, any software submitted for…
It’s been five years since Apple debuted its smartwatch, and in that time the square-faced device has become iconic and infamous. The most recent version offers ‘dimmable’ faces that keep the screen available at all times, courtesy of its low-tempera…
Memorial Day may be behind us but you can still grab some of its deals. Apple’s AirPods Pro are still at the very good sale price of $228 at Amazon, and a bunch of Fire TV devices are on sale as well. The Fire TV Cube is $100 right now and both the F…
The alum was the school’s first commencement speaker to be “standing on the spot where his dog urinated 7 minutes ago.”
Streaming is more important than ever. As huge numbers of people stay home during the global pandemic, many have turned to the plethora of services for a much-needed escape. At the start of each month, most streaming services do a little shuffle, adding new movies and taking some off, and we’re here to help with your…
Scientists have discovered a potentially new species of the adorable “dumbo” octopus in a very unique place. At more than 4 miles (6,957 meters) under the Indian Ocean, the newly discovered octo was found at the deepest depths of any cephalopod has been observed. The discovery—published in the journal Marine Biology…
In the past few days, an alarming headline has made the rounds: “Half of Fox News viewers think Bill Gates is using pandemic to microchip them, survey suggests.” This idea is nonsense, of course, but coronavirus conspiracy theories have spread almost like the virus itself across the meticulously calibrated algorithmic…
I don’t know about you, but I’m over workout earbuds that only come in dark, boring colors. The options usually range from black to grey—occasionally navy, if you’re feeling spicy. Apple-owned Beats is now giving those of us who want more color a few more shades to choose from in its Powerbeats Pro lineup, making some…
Aluminum and iconography are no longer enough for a product to get noticed in the marketplace. Today, great products need to be useful and deliver an almost magical experience, something that becomes an extension of life. Tiny Machine Learning (TinyML) is the latest embedded software technology that moves hardware into that almost magical realm, where machines can automatically learn and grow through use, like a primitive human brain.
Until now building machine learning (ML) algorithms for hardware meant complex mathematical modes based on sample data, known as “training data,” in order to make predictions or decisions without being explicitly programmed to do so. And if this sounds complex and expensive to build, it is. On top of that, traditionally ML-related tasks were translated to the cloud, creating latency, consuming scarce power and putting machines at the mercy of connection speeds. Combined, these constraints made computing at the edge slower, more expensive and less predictable.
But thanks to recent advances, companies are turning to TinyML as the latest trend in building product intelligence. Arduino, the company best known for open-source hardware is making TinyML available for millions of developers. Together with Edge Impulse, they are turning the ubiquitous Arduino board into a powerful embedded ML platform, like the Arduino Nano 33 BLE Sense and other 32-bit boards. With this partnership you can run powerful learning models based on artificial neural networks (ANN) reaching and sampling tiny sensors along with low-powered microcontrollers.
Over the past year great strides were made in making deep learning models smaller, faster and runnable on embedded hardware through projects like TensorFlow Lite for Microcontrollers, uTensor and Arm’s CMSIS-NN. But building a quality dataset, extracting the right features, training and deploying these models is still complicated. TinyML was the missing link between edge hardware and device intelligence now coming to fruition.
This is site is run by Sascha Endlicher, M.A., during ungodly late night hours. Wanna know more about him? Connect via Social Media by jumping to about.me/sascha.endlicher.
