February 11, 2021
First product is expected to launch later this year
Israeli startup NeuReality, which hopes to develop high-performance AI hardware for both cloud data centers and the edge of the network, has emerged from stealth with an $8 million seed round led by Cardumen Capital, OurCrowd, and Varana Capital.
The company, founded in 2019, says the funding will be used to launch its first product later in 2021.
NeuReality – which counts Naveen Rao, former GM of Intel’s AI products group, among its board of directors – is keeping quiet about the details of its architecture, but says the main objective is to mitigate the scaling challenges inherent in machine learning deployment.
A recent report from MIT claims that machine learning might already be approaching its computational limits, while OpenAI’s GPT-3 language model has demonstrated the huge costs – $12 million in this case – involved in training algorithms.
NeuReality’s upcoming product – which will be available as a service – promises to enable users to scale AI with lower costs and reduced energy consumption. The company claims its platform can deliver 30 times the system cost benefit over today’s top level CPU-centric servers.
Fewer challenges, more innovation
“Our mission is to deliver AI users best-in-class system performance while significantly reducing cost and power,” Moshe Tanach, founder and CEO of NeuReality, said in a statement. “We are already consuming huge amounts of AI in our day-to-day life and it will continue to grow exponentially over the next five years. In order to make AI accessible to every organization we must build affordable infrastructure that will allow innovators to deploy AI-based applications that cure diseases, improve public safety and enhance education. NeuReality’s technology will support that growth while making the world smarter, cleaner and safer for everyone.”
The company’s competition includes the likes of OctoML, Deci, DeepCube, Neural Magic and DarwinAI, but Tanach says that NeuReality is different in that it is active across three demographics: public and private cloud companies; vendors that build data center solutions and large-scale software solutions for enterprises, financial institutions, and government organizations; and OEMs and ODMs that build servers and edge node solutions.
Speaking to VentureBeat, Tanach said that NeuReality’s platform will cover all these bases. But again, he was reluctant to provide specific details, noting that, “for now, the company can only share that the total cost of ownership of its AI compute service will be more efficient by an order of magnitude compared to existing solutions.”
About the Author
You May Also Like