# Energy-Efficient ConvNets Through Approximate Computing

arXiv: https://arxiv.org/abs/1603.06777 · HTML: https://mlsanity.com/paper/1603.06777/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2016.

## Built on by (most cited first, 7 of 7)

- [FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support](https://mlsanity.com/paper/2203.06673/) (2022)
- [Hardware Acceleration of Neural Graphics](https://mlsanity.com/paper/2303.05735/) (2023)
- [Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs](https://mlsanity.com/paper/2106.03242/) (2021)
- [Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks](https://mlsanity.com/paper/2101.01543/) (2021)
- [Who Wins the Race? (R Vs Python) - An Exploratory Study on Energy Consumption of Machine Learning Algorithms](https://mlsanity.com/paper/2508.17344/) (2025)
- [Adaptive Model Compression (AMC): Saliency-Driven Resource Allocation for Ultra-Low-Power Transformer Inference](https://mlsanity.com/paper/2607.10109/) (2026)
- [Approximate reservoir computing with a semiconductor laser for reducing energy consumption](https://mlsanity.com/paper/2607.23288/) (2026)

## Abstract (arXiv)

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.