Israel startup funded to develop deep learning processor

Israel startup funded to develop deep learning processor
Business news |
Hailo Technologies Ltd. (Tel Aviv, Israel) has raised $12.5 million in a Series A round of financing to fund the development of a deep learning processor intended for embedded applications. Shown above are Hailo's founders (L-R): CEO Orr Danon, chief business development officer Hadar Zeitlin, and CTO Avi Baum.
By Peter Clarke

Share:

Investors include: Ourcrowd.com, Maniv Mobility, the Drive accelerator fund: Next Gear; as well as angel investors, Hailo Chairman Zohar Zisapel and Delek Motors CEO Gil Agmon. This latest funding round brings the total raised to date by the Tel Aviv-based company to $16 million.

The company, founded early in 2017, is the latest of scores of startups pursuing machine learning hardware but claims to have a revolutionary processor architecture to accelerate neural network processing. 

Initial samples of the deep learning processor are expected to become available in the first half of 2019. It is being designed to run embedded AI applications on edge devices that are installed in autonomous vehicles, drones, and smart home appliances such as personal assistants, smart cameras and smart TVs.

CEO Danon served in a top Israel Defense Forces technology unit and is a recipient of the Israel Defense Prize. Zeitlin also served in the same IDF technology unit for nine years and was awarded the Chief of Staff Prize for technological excellence. Baum held several senior engineering management positions at Texas Instruments, including serving as CTO for the Wireless Connectivity Group. Hailo’s development team leaders include senior hardware and software engineers, many of whom served in top technology units in the IDF and worked for companies like Intel, Broadcom and Mellanox. Hailo’s chief architect Daniel Ciubotariu, was previously a senior systems design engineer at Broadcom and was previously in the IDF.

The claim is that the Hailo processor will be provide a new PPA-cost [performance, power, area = cost] point that will be suitable for processing high-resolution sensory data in real-time.

“Hailo is revolutionizing the underlying architecture of the processor to boost deep learning processing by several orders of magnitude. We have completely redesigned the pillars of computer architecture – memory, control and compute – and the relations between them,” said Danon, Hailo CEO, in a statement.

Next: Targeting automotive


The automotive industry is one of Hailo’s target markets and one where the value of ICs designed in each year is set to nearly double between 2016 and 2021, according to IC Insights, reaching $42.9 billion in 2021, compared to $22.9 billion in 2016. Much of this growth will be due to the application of deep learning methods to advanced driver assistance systems (ADAS) and autonomous driving, Hailo expects.

Hailo said it is collaborating with major players in the industry who are examining the use of its technology.

Related links and articles:

www.hailotech.com

News articles:

Graphcore’s two-chip ‘Colossus’ close to launch

Analog NN startup signs up Infineon microphones

Stanford startup raises $56 million for ML computing

Report: Samsung invests in Chinese NN startup

ARM launches two machine learning processors

Intel to launch “commercial” Nervana NN processor in 2019

Linked Articles
eeNews Analog
10s