Binary Neural Network as a Flexible Integrated Circuit for Odour Classification
Emre Özer, Jedrzej Kufel, John Biggs, James Myers, Charles Reynolds, Gavin Brown, Anjit Rana, Antony Sou, Catherine Ramsdale, Scott White
Abstract
This paper presents the development of a binary neural network (BNN) hardware in metal-oxide thin film transistor (TFT) technology on a flexible substrate. We develop the BNN for a sweat odour application that takes data from an e-nose sensor array detecting odour, and classifies the odour. We demonstrate a fully functional BNN flexible integrated circuit (FlexIC) fabricated in 0.8μm n-type metal-oxide TFT on polyimide, consuming around 1mW power, which becomes the first neural network hardware built as a FlexIC.
Topics & Concepts
Thin-film transistorArtificial neural networkSubstrate (aquarium)Computer scienceBinary numberTransistorMaterials scienceIntegrated circuitPower (physics)Computer hardwareElectrical engineeringOptoelectronicsNanotechnologyEngineeringArtificial intelligenceLayer (electronics)PhysicsArithmeticMathematicsVoltageQuantum mechanicsGeologyOceanographyAdvanced Chemical Sensor TechnologiesGas Sensing Nanomaterials and SensorsNeural Networks and Reservoir Computing