Awards

Deci Named a Tech Innovator for Edge AI, in 2020 Gartner Report

A recent Gartner report, “Emerging Technologies: Tech Innovators in Edge AI” published October 23, 2020, named Deci one of the Edge AI Tech Innovators of 2020.

AI Innovation at the Edge is Crucial

Over the past decade, advances in AI, and more specifically deep learning, have disrupted global sectors from medical diagnosis to autonomous cars. Another important observation is that consumers now spend more time on their devices, such as mobile phones, generating large volumes of data. Businesses recognize that to remain competitive, they need to push their AI workloads closer to the devices themselves and the data, meaning to the edge.

With edge AI, the compute power available on consumer devices such as smartphones and wearables, and on enterprise devices such as robots and sensors, can run inference on the devices themselves in a distributed manner, instead of sending the data to be processed on a centralized cloud. This reduces or eliminates the need to send and process data remotely, allowing businesses to deliver improved speed, usability, and security.

According to Gartner, “Product leaders that do not innovate at the edge will struggle to remain competitive where enterprises seek optimizations and transformations enabled by edge computing and edge AI” (Emerging Technologies: Tech Innovators in Edge AI).

Gartner’s Emerging Technologies: Tech Innovators in Edge AI Report

Considering the potential value it can bring, “this report highlights technology providers that advance and accelerate the use of AI at the edge. Technology providers were selected based on the observed ability to market and sell AI-based, or AI-enabling, technologies with proven capabilities for optimization and/or transformation.” Gartner subscribers can read more here.

Blazing Fast AI Models at the Edge with Deci

As consumer behaviors and competitive landscapes rapidly change across industries, businesses need to be agile and to continuously find innovative ways to accelerate product ideation and development. However, most get stuck at some stage before deployment due to unsatisfying performance on constrained hardware, long development cycles, and compromised model accuracy, all of which affect customer experience.

Deci’s deep learning platform harnesses AI to build better AI. It automatically gears up neural networks to become top-performing production-grade solutions on any hardware, at scale. Deci’s deep learning platform, powered by AutoNAC technology (Automated Neural Architecture Construction) enables data scientists to:

  • Accelerate model inference throughput/latency by up to 10x, on any hardware, without compromising accuracy
  • Cut compute costs, including cloud and edge, by up to 80%
  • Seamlessly deploy and serve trained models to any production environment

With Deci, enterprises can deliver better and faster results at the edge.

To date, industries relating to autonomous vehicles, manufacturing, communication, video editing, healthcare, and more have already partnered with Deci and found success in using the platform.

Conclusion

The edge computing market will continue to accelerate and develop in the coming years. According to various research, the market is poised to achieve continued growth during the forecast period of 2020-2028. At Deci, we believe that to achieve AI’s true potential we need to think differently about how we develop and deploy our models to production. Achieving AI innovation at the edge will require outstanding performance on constrained hardware, and that’s exactly what we’re doing here at Deci. Come and see for yourself.

You May Also Like

Deci AI Unveils Generative AI Platform to Deliver High-Performance AI Models with Unmatched Cost Efficiency and Exceptional Control

Deci Works With Qualcomm to Make Generative AI Accessible for Wide Range of Applications

AiThority

The latest deep learning insights, tips, and best practices delivered to your inbox.

Share
Add Your Heading Text Here
				
					from transformers import AutoFeatureExtractor, AutoModelForImageClassification

extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")

model = AutoModelForImageClassification.from_pretrained("microsoft/resnet-50")