# Minimum Energy Quantized Neural Networks

arXiv: https://arxiv.org/abs/1711.00215 · HTML: https://mlsanity.com/paper/1711.00215/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2017.

## Built on by (most cited first, 21 of 21)

- [VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference](https://mlsanity.com/paper/2102.04503/) (2021)
- [hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices](https://mlsanity.com/paper/2103.05579/) (2021)
- [Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference](https://mlsanity.com/paper/2102.11289/) (2021)
- [Charged particle tracking via edge-classifying interaction networks](https://mlsanity.com/paper/2103.16701/) (2021)
- [DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos](https://mlsanity.com/paper/2203.03996/) (2022)
- [Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design](https://mlsanity.com/paper/2207.09387/) (2022)
- [Accelerating Recurrent Neural Networks for Gravitational Wave Experiments](https://mlsanity.com/paper/2106.14089/) (2021)
- [On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks](https://mlsanity.com/paper/2111.07911/) (2021)
- [Tailor: Altering Skip Connections for Resource-Efficient Inference](https://mlsanity.com/paper/2301.07247/) (2023)
- [MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos](https://mlsanity.com/paper/2210.09887/) (2022)
- [Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use](https://mlsanity.com/paper/2601.22362/) (2026)
- [An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks](https://mlsanity.com/paper/2411.06360/) (2024)
- [AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks](https://mlsanity.com/paper/2211.03741/) (2022)
- [A Learning Framework for Bandwidth-Efficient Distributed Inference in Wireless IoT](https://mlsanity.com/paper/2203.09631/) (2022)
- [Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding](https://mlsanity.com/paper/2502.08758/) (2025)
- [BitHEP -- The Limits of Low-Precision ML in HEP](https://mlsanity.com/paper/2504.03387/) (2025)
- [Link-Aware Energy-Frugal Continual Learning for Fault Detection in IoT Networks](https://mlsanity.com/paper/2512.13340/) (2025)
- [Ordinal Pooling](https://mlsanity.com/paper/2109.01561/) (2021)
- [Robust Iterative Value Conversion: Deep Reinforcement Learning for Neurochip-driven Edge Robots](https://mlsanity.com/paper/2408.13018/) (2024)
- [A Low-Complexity Plug-and-Play Deep Learning Model for Generalizable Massive MIMO Precoding](https://mlsanity.com/paper/2601.21897/) (2026)
- [GQ-FSL: Green Quantized Federated Split Learning Framework for Wireless Edge Networks](https://mlsanity.com/paper/2607.29659/) (2026)

## Abstract (arXiv)

This work targets the automated minimum-energy optimization of Quantized Neural Networks (QNNs) - networks using low precision weights and activations. These networks are trained from scratch at an arbitrary fixed point precision. At iso-accuracy, QNNs using fewer bits require deeper and wider network architectures than networks using higher precision operators, while they require less complex arithmetic and less bits per weights. This fundamental trade-off is analyzed and quantified to find the minimum energy QNN for any benchmark and hence optimize energy-efficiency. To this end, the energy consumption of inference is modeled for a generic hardware platform. This allows drawing several conclusions across different benchmarks. First, energy consumption varies orders of magnitude at iso-accuracy depending on the number of bits used in the QNN. Second, in a typical system, BinaryNets or int4 implementations lead to the minimum energy solution, outperforming int8 networks up to 2-10x at iso-accuracy. All code used for QNN training is available from https://github.com/BertMoons.