It’s no secret that the last decade has accelerated AI and Deep Learning adoption and development. However, the main issue with ML application deployment is the enormous resources it requires, starting with high performance and expensive GPUs. Israeli startup Deci develops an AI-driven platform that automatically crafts scalable deep neural network solutions, which can be integrated into a wide variety of commercial applications.
Using AI to improve AI
Advancements in AI, mainly powered by deep learning, have triggered groundbreaking innovations in medicine, manufacturing, transportation, communication, and retail. But, prolonged development cycles, high computing costs, and unsatisfying inference performance are making it nearly impossible for enterprises to productize AI. By harnessing AI to improve AI, Deci is automatically transforming models to be ready for effective production at scale. With Deci's new deep learning platform, AI developers can achieve up to tenfold performance improvement on any task, be it machine vision, NLP, or audio, thus obtaining a significant competitive advantage.
"Deci is leading a paradigm shift in AI to empower data scientists and deep learning engineers with the tools needed to create and deploy effective and powerful solutions," says Yonatan Geifman, CEO and co-founder of Deci. "The rapidly increasing complexity and diversity of neural network models make it hard for companies to achieve top performance. We realized that the optimal strategy is to harness the AI itself to tackle this challenge. Using AI, Deci's goal is to help every AI practitioner to solve the world's most complex problems."
Israeli startup Deci leverages Machine-Learning technologies to automatically optimize the neural network, so they will operate more efficiently and at scale. The company’s Deep Learning platform automatically gears up neural networks to become top-performing production-grade solutions on any hardware, including CPUs, GPUs, and special-purpose AI chips for edge and mobile. The platform is powered by Deci's patent-pending AutoNAC (Automated Neural Architecture Construction) technology, which uses Machine Learning to redesign any model and maximize its inference performance. The platform optimizes any given Deep Learning model and cuts its computing costs for any desired hardware.
"In contrast to most classical Machine Learning algorithms, in Deep Learning, it's much easier to achieve shining out-of-sample accuracy with very large, over-parameterized, but very slow neural networks," said Professor Ran El-Yaniv, Deci's Chief Scientist, "Our AutoNAC performs a smart high-speed search across a huge set of neural network architectures to aggressively speedup runtime, while preserving accuracy, by optimizing the fit between the neural network structure, the user's dataset, and the target computing hardware."
Last month, Deci submitted its inference results to MLPerf, the industrial standard for Deep-Learning performance. On several popular Intel CPUs, Deci accelerated the inference speed of the well-known ResNet neural network by 11.8x while meeting the MLPerf accuracy target. An acceleration of this magnitude closes the gap between the latency of inference on CPU and standard GPUs. This is a significant step towards enabling deep learning inference on millions of available CPUs, both on cloud, enterprise data centers, and edge devices.
Deci was co-founded by Deep Learning scientist Yonatan Geifman, PhD, together with tech entrepreneur Jonathan Elial, and professor Ran El-Yaniv, a computer scientist and Machine Learning expert. Deci has already recruited a core team of top-notch Deep Learning engineers and scientists, with vast experience in elite organizations and universities. The startup’s $9.1 million Seed funding round was led by venture capitalist firm Emerge and Square Peg. With 17 employees based in offices in Israel, the company plans to use the new capital to continue talent recruitment.