Deci AI · raw details

Deci AI is focused on enabling deep learning to live up to its true potential by using artificial intelligence to build better artificial intellgience. The company’s end-to-end deep-learning acceleration platform allows AI developers to build, optimize, and deploy faster, more accurate models for any environment, including cloud, edge, or mobile.

With Deci’s platform, developers can increase deep-learning model inference performance by three to 15 times, on any hardware, while still preserving accuracy. This translates directly into new use cases on limited hardware, substantially shorter development cycles, and compute costs reduced 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 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.

Teams are currently building DNN architectures that consume anywhere from 30% to 80% less compute power for inference with Deci’s Neural Architecture Search (NAS) deep-learning development platform.

Deci achieved an 11.8-times accelerated inference speedup on Intel CPUs at MLPerf Industry Benchmark and has been named one of CBInsights’ top 100 AI companies.