Skip to main content
https://www.highperformancecpmgate.com/rgeesizw1?key=a9d7b2ab045c91688419e8e18a006621

Deci raises $9.1M to optimize AI models with AI

Deci, a Tel Aviv-based startup that is building a new platform that uses AI to optimized AI models and get them ready for production, today announced that it has raised a $9.1 million seed round led by Emerge and Square Peg.

The general idea here is to make it easier and faster for businesses to take AI workloads into production — and to optimize those production models for improved accuracy and performance. To enable this, the company built an end-to-end solution that allows engineers to bring in their pre-trained models and then have Deci manage, benchmark and optimize them before they package them up for deployment. Using its runtime container or Edge SDK, Deci users can also then serve those models on virtually any modern platform and cloud.

Deci’s insights screen combines all indicators of a deep learning model’s expected behavior in production, resulting in the Deci Score – a single metric summarizing the overall performance of the model.

The company was co-founded by co-founded by deep learning scientist Yonatan Geifman, technology entrepreneur Jonathan Elial, and professor Ran El-Yaniv, a computer scientist and machine learning expert at the Technion – Israel Institute of Technology.

“Deci is leading a paradigm shift in AI to empower data scientists and deep learning engineers with the tools needed to create and deploy effective and powerful solutions,” says Yonatan Geifman, CEO and co-founder of Deci. “The rapidly increasing complexity and diversity of neural network models make it hard for companies to achieve top performance. We realized that the optimal strategy is to harness the AI itself to tackle this challenge. Using AI, Deci’s goal is to help every AI practitioner to solve the world’s most complex problems.”

Deci’s lab screen enables users to manage their deep learning models’ lifecycles, optimize inference performance, and prepare models for deployment. Image Credits: Deci

The company promises is that, on the same hardware and with comparable accuracy, Deci-optimized models will run between five and ten times faster than before. It can make use of CPUs and GPUs for running its inference workloads and the company says that it is already working with customers in autonomous driving, manufacturing, communication and healthcare, among others.

“Deci‘s ability to automatically craft top-performing deep learning solutions is a paradigm shift in artificial intelligence and unlocks new opportunities for many businesses across different industries,” said Liad Rubin, Partner at Emerge. “We are proud to have partnered with such incredible founders and be part of Deci’s journey from day one.”

 

Comments

Post a Comment

Popular posts from this blog

Uber co-founder Garrett Camp steps back from board director role

Uber co-founder Garrett Camp is relinquishing his role as a board director and switching to board observer — where he says he’ll focus on product strategy for the ride hailing giant. Camp made the announcement in a short Medium post in which he writes of his decade at Uber: “I’ve learned a lot, and realized that I’m most helpful when focused on product strategy & design, and this is where I’d like to focus going forward.” “I will continue to work with Dara [Khosrowshahi, Uber CEO] and the product and technology leadership teams to brainstorm new ideas, iterate on plans and designs, and continue to innovate at scale,” he adds. “We have a strong and diverse team in place, and I’m confident everyone will navigate well during these turbulent times.” The Canadian billionaire entrepreneur signs off by saying he’s looking forward to helping Uber “brainstorm the next big idea”. Camp hasn’t been short of ideas over his career in tech. He’s the co-founder of the web 2.0 recommendatio
Post a Comment
Read more

Drone crash near kids leads Swiss Post and Matternet to suspend autonomous deliveries

A serious crash by a delivery drone in Switzerland have grounded the fleet and put a partnership on ice. Within a stone’s throw of a school, the incident raised grim possibilities for the possibilities of catastrophic failure of payload-bearing autonomous aerial vehicles. The drones were operated by Matternet as part of a partnership with the Swiss Post (i.e. the postal service), which was using the craft to dispatch lab samples from one medical center for priority cases. As far as potential applications of drone delivery, it’s a home run — but twice now the craft have crashed, first with a soft landing and the second time a very hard one. The first incident, in January, was the result of a GPS hardware error; the drone entered a planned failback state and deployed its emergency parachute, falling slowly to the ground. Measures were taken to improve the GPS systems. The second failure in May, however, led to the drone attempting to deploy its parachute again, only to sever the line
Post a Comment
Read more

ProtonMail logged IP address of French activist after order by Swiss authorities

ProtonMail , a hosted email service with a focus on end-to-end encrypted communications, has been facing criticism after a police report showed that French authorities managed to obtain the IP address of a French activist who was using the online service. The company has communicated widely about the incident, stating that it doesn’t log IP addresses by default and it only complies with local regulation — in that case Swiss law. While ProtonMail didn’t cooperate with French authorities, French police sent a request to Swiss police via Europol to force the company to obtain the IP address of one of its users. For the past year, a group of people have taken over a handful of commercial premises and apartments near Place Sainte Marthe in Paris. They want to fight against gentrification, real estate speculation, Airbnb and high-end restaurants. While it started as a local conflict, it quickly became a symbolic campaign. They attracted newspaper headlines when they started occupying prem
Post a Comment
Read more