Photonic Technology Lighting the Way
Machine-Learning is becoming ubiquitous in modern societies and virtually impacting every industry. However, the demand for machine-learning hardware is extraordinary and no current solution is capable of supplying demand (trend exacerbating).
Our team has demonstrated photonic-based solution enabled by the unique scaling laws in optics, thus opening opportunities for revolutionary photonic machines ‘lighting-the-way’ for 21st century key tasks in decision-making, data analytics, and machine intelligence.
Within this scope there is a rationale for using optics/photonics for information processing due to unprecedented signal processing capabilities (speed-of-light), massive parallelism, non-iterative processors.
We are developing solution for: How can we design/engineer revolutionary information processing systems with 100-1000x improvements WRT data speed and efficiency? What exciting new avenues in real-time intelligent decision-making can photonic-based processing enable?
We believe in innovations that are vetted both by applied-science and fundamental-engineering. We pride ourselves to shape the future of optical information processing crossing mixed-signal domains, computing accelerators for a broad range of applications spanning defense, semiconductor, computing, intelligence, car industry, health-care.
Photonic Tensor Core Processor
Integrated photonic platforms that integrate efficient optical memory can obtain the same operations as a tensor processing unit (TPU), but they consume a fraction of the power and have higher throughput and, when opportunely trained, can be used for performing inference at the speed of light.Optelligence also solved the electronic-to-optical domain crossings by developing an efficient digital-to-analog converter on photonic circuits.
Massively-parallel Optical Convolution Neural Network Processor
With funding from Office of Naval Research (ONR) , Optelligence Company, developed an optical convolutional neural network accelerator capable of processing large amounts of information, on the order of petabytes, per second. This innovation, which harnesses the massive parallelism of light, heralds a new era of optical signal processing for machine learning with numerous applications, including in self-driving cars, #5G networks, #datacenters, biomedical diagnostics, #datasecurity.