Analog machine learning chip delivers always-on power efficiency
Stephen LawElectronics Power Supply / Management Semiconductors machine learning power semiconductor
ASPINITY analogML family AML100 tiny machine learning (ML) solution operates completely within the analog domain. Product reduces always-on system power by 95%, allowing manufacturers to dramatically extend the battery life of today’s devices or migrate walled powered always-on devices to battery. — Chip boosts battery life by up to 20x with innovative system-level approach to always-on power reduction. AML100 delivers substantial system-level power-savings by moving the ML workload to ultra-low-power analog, where the chip can determine data relevancy with a high degree of accuracy and at near-zero power. Chip intelligently reduces data at the sensor while the data is still analog and keeps the digital components in low power mode until important data is detected, thereby eliminating the power penalty of digitization, digital processing, and transmission of irrelevant data.