Researchers tried out several new devices to get closer to the ideal needed for deep learning and neuromorphic computing What’s the best type of device from which to build a neural network? Of course, it should be fast, small, consume little power, have the ability to reliably store many bits-worth of information. And if it’s going to be involved in learning new tricks as well as performing those tricks, it has to behave predictably during the learning process. Neural networks can be thought of as a group of cells connected to other cells. These connections—synapses in biological neurons—all have particular strengths, or weights, associated with them. Rather than use the logic and memory of ordinary CPUs to represent these, companies and academic researchers have been working on ways of representing them in arrays of different kinds of nonvolatile memories. That way, key computations can be made without having to move Continue reading Searching for the Perfect Artificial Synapse for AI
In a quest for penny-priced plastic sensors, Arm and its partners are demonstrating a stripped-down form of machine learning Body odor is a stubborn problem. Not just for people, but also for sensors. Sensors and the computing attached to them struggle to perceive armpit odors in the way humans do, because B.O. is really a complex mix of dozens of gaseous chemicals. The UK’s PlasticArmPit project is designing the first machine learning–enabled flexible plastic sensor chip. Its target audience: those who think they might stink. The prototype chip will be manufactured and tested in 2019. The project is part of a broader effort Arm has been involved in to drive the cost of plastic IoT devices down below US $0.01 so that they can be embedded in all sorts of consumer goods, including disposable ones.
Bandwidth limits mean AI systems need too much DRAM, embedded-FPGA startup thinks its technology can change that Deep learning has a DRAM problem. Systems designed to do difficult things in real time, such as telling a cat from a kid in a car’s backup camera video stream, are continuously shuttling the data that makes up the neural network’s guts from memory to the processor. The problem, according to startup Flex Logix, isn’t a lack of storage for that data; it’s a lack of bandwidth between the processor and memory. Some systems need four or even eight DRAM chips to sling the 100s of gigabits to the processor, which adds a lot of space and consumes considerable power. Flex Logix says that the interconnect technology and tile-based architecture it developed for reconfigurable chips will lead to AI systems that need the bandwidth of only a single DRAM chip and consume one-tenth Continue reading Flex Logix Says It’s Solved Deep Learning’s DRAM Problem
Chip can learn on its own and inference at 100-microwatt scale company says at Arm Tech Con At Arm Tech Con today, West Lake Village, Calif.-based startup Eta Compute showed off what it believes is the first commercial low-power AI chip capable of learning on its own using a type of machine learning called spiking neural networks. Most AI chips for use in low-power or battery-operated IoT devices have a neural network that has been trained by a more powerful computer to do a particular job. A neural network that can do what’s called unsupervised learning can essentially train itself: Show it a pack of cards and it will figure out how to sort the threes from the fours from the fives. Eta Compute’s third generation chip, called TENSAI, also does traditional deep learning using convolutional neural networks. Potential customers already have samples of the new chip, and the company expects Continue reading Eta Compute Debuts Spiking Neural Network Chip for Edge AI
In the intensive care unit, artificial intelligence can keep watch at a patient’s bedside Illustration: MCKIBILLO In a hospital’s intensive care unit (ICU), the sickest patients receive round-the-clock care as they lie in beds with their bodies connected to a bevy of surrounding machines. This advanced medical equipment is designed to keep an ailing person alive. Intravenous fluids drip into the bloodstream, while mechanical ventilators push air into the lungs. Sensors attached to the body track heart rate, blood pressure, and other vital signs, while bedside monitors graph the data in undulating lines. When the machines record measurements that are outside of normal parameters, beeps and alarms ring out to alert the medical staff to potential problems. While this scene is laden with high tech, the technology isn’t being used to best advantage. Each machine is monitoring a discrete part of the body, but the machines aren’t working in concert. The Continue reading AI Could Provide Moment-by-Moment Nursing for a Hospital’s Sickest Patients
TSMC is the big winner, having made them both At an event today, Apple executives said that the new iPhone Xs and Xs Max will contain the first smartphone processor to be made using 7 nm manufacturing technology, the most advanced process node. Huawei made the same claim, to less fanfare, late last month and it’s unclear who really deserves the accolades.
IBM’s new chip is designed to do both high-precision learning and low-precision inference across the three main flavors of deep learning The field of deep learning is still in flux, but some things have started to settle out. In particular, experts recognize that neural nets can get a lot of computation done with little energy if a chip approximates an answer using low-precision math. That’s especially useful in mobile and other power-constrained devices. But some tasks, especially training a neural net to do something, still need precision. IBM recently revealed its newest solution, still a prototype, at the IEEE VLSI Symposia: a chip that does both equally well.
Deal with Microsemi and foundries means its nonvolatile embedded memory can be integrated into the most advanced chips Photo: Crossbar Resistive RAM technology developer Crossbar says it has inked a deal with aerospace chip maker Microsemi allowing the latter to embed Crossbar’s nonvolatile memory on future chips. The move follows selection of Crossbar’s technology by a leading foundry for advanced manufacturing nodes. Crossbar is counting on resistive RAM (ReRAM) to enable artificial intelligence systems whose neural networks are housed within the device rather than in the cloud. ReRAM is a variant of the memristor, a nonvolatile memory device whose resistance can be set or reset by a pulse of voltage. The variant Crossbar qualified for advanced manufacturing is called a filament device. It’s built within the layers above a chip’s silicon, where the IC’s interconnects go, and it’s made up of three layers: from top to bottom—silver, amorphous silicon, and Continue reading Crossbar Pushes Resistive RAM into Embedded AI
Mixer IC works at 500 degrees Celsius, so it can take the heat on the surface of Venus, inside a natural gas turbine, or in the bowels of a 6-kilometer deep oil well Photo: KTH Royal Institute of Technology/University of Arkansas/IEEE There are still some places the Internet of Things fears to tread. Researchers at the University of Arkansas and the KTH Royal Institute of Technology, in Sweden, are building a radio for those places. This month, in IEEE Electron Device Letters, they describe a mixer, a key component of any wireless system, that works just fine from room temperature all the way up to 500 ºC. It’s the first mixer IC capable of handling such extremes. IEEE Fellow and Arkansas professor of electrical engineering Alan Mantooth specializes in electronics for extreme environments. Of several projects “one of the more sexy is trying to put a rover or some sort of instrument Continue reading Making Radio Chips for Hell
Key applications include privacy-preserving home monitoring Photo: Vayyar Last week, Israeli radar chip startup Vayyar Imaging released a new, higher resolution 3D imaging radar chip it expects will appear in applications as broad as home security, infotainment, and elder care. The resolution is higher, because it packs an unprecedented 72 transceivers on a chip that has its own digital signal processing circuitry. But the image it creates is nothing like a visible light camera’s, and that’s the key, according the company’s CEO and cofounder Raviv Melamed. “One of the biggest problems, if you want to monitor people in their home, is privacy,” says Melamed. “Obviously, the best thing to have is a camera, but nobody really wants a camera in the house, especially when people can hack in.” He thinks Vayyar’s chip, which forms images at radar frequencies between 3 GHz to 81 GHz, can provide all the information needed Continue reading Vayyar’s 72-Transceiver Radar Chip Sees Just Enough But Not Too Much