DeepCube’s pioneering inference accelerator drastically improves performance on additive manufacturing hardware
____________________________________________________________________________________________
Real-Time Error Detection and Correction
DeepCube applies the same neural network training behind photo and speech recognition advancements to the manufacturing of parts.
Improved Part Quality
Multiple sensors can spot defects too small for the human eye.
Increased Part Yield
AI-driven decision making corrects printing errors in real time.
“Many companies will only leverage machine learning or AI to the extent that its results are intuitive and transparent and, in some industries, explainable to external regulators. The importance of this transparency came through in our survey: 67 percent of leaders track traceability of outcomes, compared with only 14 percent of the rest.”
Toward smart production:
Machine intelligence in business
operations. McKinsey & Company
Unrivaled Data Speeds
DeepCube’s propriety algorithms increase the speeds of data analysis tenfold, making it the only hardware performance accelerator of its kind.
Memory Usage Reduction
Overcomes the infrastructure, energy, and memory limitations of previous AI models for low-cost deployment.
From Datacenter to Edge
The leap forward in software processing allows AI to take on an active role in edge device control.
Distributed Global Automation
Artificial intelligence turns machines into nodes. DeepCube transforms 3D printers into a viable global solution for the demands of Industry 4.0.
Production-Minded
DeepCube can coordinate multiple machines across a lab or across the world.
Learning Across the Network
Machines share learning inferences with each other for immediate adjustments in production flow.