- Deeplite, a startup based in Montreal.
- Deeplite raises a $6 million seed investment.
- PJC led the round, with help from Innospark Ventures, Differential Ventures and Smart Global Holdings.
- The company has created a product called Neutrino.
- The idea is to run a machine learning application on an extremely small footprint.
Deeplite creates intelligent optimization software for deep learning deployed on cloud servers and edge devices. Deeplite provides a platform that uses AI to automatically make other AI models smaller, faster, and more energy efficient creating compact, high-performance deep neural networks that can run at the “edge” in vehicles, cameras, sensors,drones, phones.
A significant challenge with deep learning models is that they are too large to deploy on small hardware, too slow to process mission critical applications or compromise battery life. Deeplite solves this problem by using a fully automated, proprietary and patented AI engine to optimize DNN models so that they can be deployed to any hardware platform on any device. .
Our technology leverages years of research and new developments in tinyML to produce fast, efficient and scalable deep learning solutions for challenging real-world environments.
Deeplite raises $6 Million seed to deploy ML on edge with fewer compute resources.
It is a startup based in Montreal, wants to change that by providing a way to reduce the overall size of the model, allowing it to run on hardware with far fewer resources.
The company announces a $6 million seed investment. Boston-based venture capital firm PJC led the round, with help from Innospark Ventures, Differential Ventures and Smart Global Holdings. Somel Investments, BDC Capital and Desjardins Capital also participated.
Nick Romano, CEO and co-founder at Deeplite, says the company aims to take complex deep neural networks that require a lot of compute power to run, tend to use up a lot of memory and can consume batteries at a rapid pace, and help them run more efficiently with fewer resources.
Deeplite’s platform can be used to transform models on hardware at the edge.
Our platform can be useful in transforming those models into a new form factor. And then we will be able to deploy it into constrained hardware at the edge.”
Those devices could be as small as a cell phone, a drone or even a Raspberry Pi. This means that the developers could deploy AI in ways that just wouldn’t be possible in most cases right now.
The company has created a product called Neutrino. It lets you specify how you want to deploy your model and how much you can compress it. You can reduce the overall size and the resources required to run it in production.
The idea is to run a machine learning application on an extremely small footprint.