# Resource-Efficient Neural Networks for Embedded Systems

arXiv: https://arxiv.org/abs/2001.03048 · HTML: https://mlsanity.com/paper/2001.03048/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2020.

## Built on by (most cited first, 20 of 20)

- [S-Rocket: Selective Random Convolution Kernels for Time Series Classification](https://mlsanity.com/paper/2203.03445/) (2022)
- [Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation](https://mlsanity.com/paper/2201.10360/) (2022)
- [System Safety Monitoring of Learned Components Using Temporal Metric Forecasting](https://mlsanity.com/paper/2405.13254/) (2024)
- [Compressing the Backward Pass of Large-Scale Neural Architectures by Structured Activation Pruning](https://mlsanity.com/paper/2311.16883/) (2023)
- [A Dimensionality Reduction Approach for Convolutional Neural Networks](https://mlsanity.com/paper/2110.09163/) (2021)
- [Efficient Similarity-based Passive Filter Pruning for Compressing CNNs](https://mlsanity.com/paper/2210.17416/) (2022)
- [Quantization Effects on Neural Networks Perception: How would quantization change the perceptual field of vision models?](https://mlsanity.com/paper/2403.09939/) (2024)
- [Efficient and Flexible Method for Reducing Moderate-size Deep Neural Networks with Condensation](https://mlsanity.com/paper/2405.01041/) (2024)
- [Deep Learning Techniques for Hand Vein Biometrics: A Comprehensive Review](https://mlsanity.com/paper/2409.07128/) (2024)
- [Understanding Cache Boundness of ML Operators on ARM Processors](https://mlsanity.com/paper/2102.00932/) (2021)
- [Less Memory Means smaller GPUs: Backpropagation with Compressed Activations](https://mlsanity.com/paper/2409.11902/) (2024)
- [Binarized Weight Error Networks With a Transition Regularization Term](https://mlsanity.com/paper/2105.03897/) (2021)
- [Guaranteed Quantization Error Computation for Neural Network Model Compression](https://mlsanity.com/paper/2304.13812/) (2023)
- [Implications of Noise in Resistive Memory on Deep Neural Networks for Image Classification](https://mlsanity.com/paper/2401.05820/) (2024)
- [From Theory to Practice: Implementing and Evaluating e-Fold Cross-Validation](https://mlsanity.com/paper/2410.09463/) (2024)
- [Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation](https://mlsanity.com/paper/2511.23440/) (2025)
- [Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification](https://mlsanity.com/paper/2512.10602/) (2025)
- [TinyNeRV: Compact Neural Video Representations via Capacity Scaling, Distillation, and Low-Precision Inference](https://mlsanity.com/paper/2604.09220/) (2026)
- [Efficient Neural Network Model Selection for Few-Class Application Datasets](https://mlsanity.com/paper/2606.19712/) (2026)
- [Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference](https://mlsanity.com/paper/2609.15527/) (2026)

## Abstract (arXiv)

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment with virtually unlimited computing resources into everyday's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. In particular, we focus on resource-efficient inference based on deep neural networks (DNNs), the predominant machine learning models of the past decade. We give a comprehensive overview of the vast literature that can be mainly split into three non-mutually exclusive categories: (i) quantized neural networks, (ii) network pruning, and (iii) structural efficiency. These techniques can be applied during training or as post-processing, and they are widely used to reduce the computational demands in terms of memory footprint, inference speed, and energy efficiency. We also briefly discuss different concepts of embedded hardware for DNNs and their compatibility with machine learning techniques as well as potential for energy and latency reduction. We substantiate our discussion with experiments on well-known benchmark data sets using compression techniques (quantization, pruning) for a set of resource-constrained embedded systems, such as CPUs, GPUs and FPGAs. The obtained results highlight the difficulty of finding good trade-offs between resource efficiency and prediction quality.