A Fully-Integrated Analog Machine Learning Classifier for Breast Cancer Classification
Sanjeev Tannirkulam Chandrasekaran, Ruobing Hua, Imon Banerjee, Arindam Sanyal
Abstract
We propose a fully integrated common-source amplifier based analog artificial neural network (ANN). The performance of the proposed ANN with a custom non-linear activation function is demonstrated on the breast cancer classification task. A hardware-software co-design methodology is adopted to ensure good matching between the software AI model and hardware prototype. A 65 nm prototype of the proposed ANN is fabricated and characterized. The prototype ANN achieves 97% classification accuracy when operating from a 1.1 V supply with an energy consumption of 160 fJ/classification. The prototype consumes 50 μ W power and occupies 0.003 mm 2 die area.
Topics & Concepts
Artificial neural networkClassifier (UML)SoftwareComputer scienceActivation functionArtificial intelligencePower consumptionAmplifierPattern recognition (psychology)Electronic engineeringComputer hardwareBandwidth (computing)Embedded systemEngineeringPower (physics)Operating systemTelecommunicationsQuantum mechanicsPhysicsAnalog and Mixed-Signal Circuit DesignCCD and CMOS Imaging SensorsNeural Networks and Applications