Energy-Efficient ConvNets Through Approximate Computing
This work addresses energy efficiency for ConvNets in wearable and IoT devices, representing an incremental improvement through hybrid techniques.
The paper tackled the problem of high energy consumption in ConvNet accelerators for embedded systems by proposing approximate computing methods, achieving up to 30x energy reduction without accuracy loss and over 100x at 99% accuracy compared to 16-bit fixed point.
Recently ConvNets or convolutional neural networks (CNN) have come up as state-of-the-art classification and detection algorithms, achieving near-human performance in visual detection. However, ConvNet algorithms are typically very computation and memory intensive. In order to be able to embed ConvNet-based classification into wearable platforms and embedded systems such as smartphones or ubiquitous electronics for the internet-of-things, their energy consumption should be reduced drastically. This paper proposes methods based on approximate computing to reduce energy consumption in state-of-the-art ConvNet accelerators. By combining techniques both at the system- and circuit level, we can gain energy in the systems arithmetic: up to 30x without losing classification accuracy and more than 100x at 99% classification accuracy, compared to the commonly used 16-bit fixed point number format.