Deep learning models are emerging everywhere and can affect almost every aspect of human life. But the creation of deep learning models and their deployment, are limited today by human expertise and by the computing resources required for their operation in production. Deci’s platform bridges those expertise and computational gaps, helping deep learning engineers and practitioners blast through the AI barrier, enabling them to deliver state-of-the-art models faster than ever. Our proprietary AutoML technology leverages hidden structures in the data and squeezes maximum utilization out of the hardware, to achieve a sweet spot that boosts the efficiency, speed, and accuracy of any deep learning model, for any production hardware.

Deci enables deep learning to live up to its true potential by using AI to build better AI. With the company’s end-to-end deep learning acceleration platform, AI developers can build, optimize, and deploy faster and more accurate models for any environment, including cloud, edge, or mobile. With Deci’s platform, developers can increase deep learning model inference performance by 3x-15x, on any hardware, while still preserving accuracy. This translates directly into new use cases on limited hardware, substantially shorter development cycles, and reduced compute costs by up to 80%. The platform is powered by Deci’s Automated Neural Architecture Construction (AutoNAC) technology, an algorithmic optimization engine that squeezes maximum utilization out of any hardware. The AutoNAC engine contains a Neural Architecture Search (NAS) component that redesigns a given trained model’s architecture to optimally improve its inference performance (throughput, latency, memory, etc.) for specific target hardware while preserving its baseline accuracy. Deci achieved a record-breaking 11.8x accelerated inference speedup on Intel CPUs at MLPerf Industry Benchmark and has been named to the CBInsights top 100 AI compan