The Silicon Review
Artificial intelligence lies at the core of the fourth Industrial Revolution. Advanced technologies such as AI are impacting humankind more than ever before. Founded in 2019, Deci's mission is to enable AI developers and engineers to focus on what they do best - solving our world’s most complex problems. At the same time, the team at Deci challenge itself with how to enable more and more of these machine learning and deep learning models to fully perform in production and fulfill their true potential.
At Deci, the team takes an innovative approach to this challenge, using AI itself to craft the next generation of deep learning. The company has developed an algorithmic-first approach, focused on improving the efficacy of AI algorithms, delivering to its customers models that outperform the advantages of any other hardware or software optimization technologies.
Deci was created by world recognized experts in AI, with an innate passion for creative innovation. The company forged a talented team of deep learning researchers and engineers. Deci’s team is armed with advanced academic degrees from prestigious universities, as well as exceptional backgrounds in elite units and leading tech companies. Its team of experts is fully dedicated to advancing the state-of-the-art and has co-authored dozens of publications in top-tier machine learning venues such as NeurIPS, ICML, ICLR, CVPR, and ACL.
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 companies. Led by a team of world-class deep learning experts, Deci lets AI developers focus on what they do best - creating innovative AI-based solutions for our world’s most complex problems.
Deci Platform is a SaaS platform that is available as a managed web application, HTTP API and self-hosted solution. It supports one or more clients and is available in a variety of programming languages and protocols.
Deci AI’s proprietary Automated Neural Architecture Construction (AutoNAC) engine provides a substantial performance boost to existing deep neural solutions. The acceleration provided by its cutting-edge algorithmic acceleration technology autonomously redesigns your deep learning models in order to provide dramatically increased throughput, significant reductions in inference latency and substantial cost-to-serve savings, which are often accompanied by improvements in accuracy.
This is Deci’s most powerful optimization feature and provides up to 10X performance boost and up to 80% cost-savings, while preserving the model’s trained accuracy.
AutoNAC is hardware-aware. It optimizes deep models to more effectively use their hardware platform (whether it is a CPU, GPU, FPGA or special purpose ASIC accelerator) in order to reach top performance during production.
As input, the AutoNAC process receives the customer baseline model, the data used to train this model, and access to the target inference hardware device. AutoNAC then revises the baseline backbone layers that carry out most of the computation and redesign to be an optimal sub-network. This optimization is carried out by performing a very efficient predictive search in a large set of candidate architectures. During this process, AutoNAC probes the target hardware and directly optimizes the runtime, as measured on this specific device. The final fast architecture is then fine-tuned on the data provided, to achieve the same accuracy performance as the baseline. It is then ready for deployment.
About the Leader
Yonatan Geifman, Co-founder and CEO
Under Yonatan's leadership, Deci has been recognized as Tech Innovator for Edge AI by Gartner and included in CB Insights’ AI 100 list. Its proprietary technology’s performance set new records at MLPerf with Intel.
Before founding Deci, Yonatan was a research intern at Google AI’s MorphNet team. He received his Ph.D. in Computer Science at the Technion-Israel Institute of Technology. His research focused on making Deep Neural Networks (DNNs) more reliable for mission-critical tasks by estimating and controlling their uncertainty at production time. It has been published and presented at leading global conferences including NeurIPS, ICML, and ICLR.