Making Machine Learning More Energy Efficient by Bringing It Closer to the Sensor

Processing data close to the sensor on a low-cost, low-power embedded device has the potential to unlock new areas for machine learning (ML). Whether it is possible to deploy such ML applications or not depends on the energy efficiency of the solution. One way to realize lower energy consumption is to bring the application as close as possible to the sensor. We demonstrate the concept of transforming an ML application running near the sensor into a hybrid near-sensor in-sensor application. This approach aims to reduce overall energy consumption and we showcase it using a motion classification example, which can be considered a simpler subproblem of activity recognition. The reduction of energy consumption is achieved by combining a convolutional neural network with a decision tree. Both applications are compared in terms of accuracy and energy consumption, illustrating the benefits of the hybrid approach.