NVIDIA's third GPU Technology Conference in just over a month spilled across Tel Aviv's convention center this week, in a packed show featuring a live demo of an AI-infused apple-picking drone, a student-built autonomous Formula One car and a two-person company that ran away with the title of Israel's hottest startup.

The second annual GTC Israel show drew 2,000 attendees, up 75 percent from last year, on the back of recent sellout crowds in at GTCs in Tokyo and Munich. It was wall to wall with the companies that have won Israel the moniker of 'startup nation.' Indeed, there are more than 4,000 tech startups in a country of 8.5 million, or 40x the density of startups in the U.S.

None flew higher at the show than Inception award winner TheWhollySee, a winkingly named shop with just two full-time employees that creates high-fidelity image datasets for training and certifying the AI brains of autonomous vehicles.

Its founder, Dan Yanson, said the first thing he'd do with the prize - $100,000 in cash plus an NVIDIA DGX Station personal AI supercomputer - is to bring his two part-timers fully on board.

'My first reaction? I'm just overwhelmed,' said Yanson, who studied in Sweden and Russia before completing his Ph.D. from the University of Glasgow. 'We're really a baby company - it's a small team, we haven't raised a lot of money yet and the competition was extremely strong. The prize money is a great boost, but it's the DGX Station that will be a springboard to accelerate us, both in terms of our technology and our business.'

Yanson competed against seven other startups - in fields that included healthcare, agriculture, retail and esports - in a back-to-back series of five-minute presentations and then Q&A with a four-person panel. He briskly described the company's ability to infuse imagery into the foreground of scenes to more rapidly train neural networks for self-driving cars

The Inception awards, which drew a crowd of more than 300 sitting largely nightclub style in a soaring black-walled space, capped off a day that had started with a blistering keynote about NVIDIA's mission to accelerate computing by NVIDIA Chief Scientist Bill Dally.

Dally announced that NVIDIA has just named a long-time Google Brain researcher, Gal Chechik, to the newly created position of Israel Research Head. Chechik's mission: to build a world-class team focused on research into deep learning for smarter perception - including combining vision with language and knowledge, learning to generalize more broadly, and understanding complex data.

Along with some 450 individuals who received training from the Deep Learning Institute and 50+ talks by AI experts, the show included a teeming exhibition hall.

Among its hottest draws was a large netted structure where Tevel Aerobotics showed off its autonomous drone which can gingerly pick, thin and prune fruit trees, relieving the labor crunch in the agriculture sector, while helping farmers' margins.

And a team of undergrads from Israel's top-ranked Technion University showed off their side project developing an AI-powered mini-Formula One car, which they're in the process of converting from gas-powered to all electric.

Other finalists in the Inception awards included:

Blink (esports) - Aiming at the rapidly growing esports market, the company focuses on what it estimates as 600 million gamers and gaming enthusiasts who want to share their favorite moments online. Its platform focuses on the social side of esports by automatically detecting great gaming moments, saving them and making them easily shareable online.

IBEX Medical Analytics (Healthcare) - This two-year-old startup applies AI and big data to support pathologists in diagnosing types of cancer. Its work is focused on developing products that improve clinical decision making, streamline laboratory workflows and enable predictive, personalized cancer treatments.

Jungo Connectivity (Automotive) - This Cisco spinoff offers in-car AI software focused on no-driver monitoring and cabin sensing, enabling vehicles to make better decisions and protect their driver and passengers. Its CoDriver SDK provides deep learning, machine learning and computer vision algorithms to OEMs and tier-1 suppliers, enabling them to create next-gen driver and occupant monitoring systems.

Tevel Aerobotics (Agriculture) - This two-year-old startup addresses the shortage of labor in the agricultural sector, by developing a fleet of autonomous airborne drones for picking, thinning and pruning fruit trees, enhancing productivity and saving costs. It promotes its solution as cost effective, flexible, easy to operate and enabling fruit trees to grow higher, thus maximizing yields and improving farmers' margins.

TRACXPOiNT (Retail) - Aiming to bring the convenience of online shopping to retail, the company has created an AI-infused, self-checkout shopping cart. Using visual detection with deep learning capabilities, its AIC cart recognizes customers, transfers their shopping list to its monitor, automatically finds and recognizes products, while offering coupons, and provides automatic checkout.

Voiceitt (Healthcare) - Its proprietary technology enables individuals with non-standard speech - such as stroke victims or those with muscle-related disabilities - to have their vocal expressions translated into clear speech, in real time. Its technology can be integrated with smart assistants, such as Alexa, to provide new levels of independence for those otherwise unable to carry out many simple actions.

WayCare (Smart Cities) - In a world of ever-worsening traffic conditions, the company is focusing on providing municipalities with the ability to harness in-vehicle information and traffic data to optimize roadways. It uses CCTVs, traffic accident information, telematics, traffic detectors, weather forecasts and other data sources to extract, compile and analyze data for improving traffic flows.

Attachments

  • Original document
  • Permalink

Disclaimer

Nvidia Corporation published this content on 18 October 2018 and is solely responsible for the information contained herein. Distributed by Public, unedited and unaltered, on 18 October 2018 18:12:08 UTC