# Hardware-oriented Approximation of Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1604.03168 · HTML: https://mlsanity.com/paper/1604.03168/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2016.

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

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [SPIQ: Data-Free Per-Channel Static Input Quantization](https://mlsanity.com/paper/2203.14642/) (2022)
- [MKQ-BERT: Quantized BERT with 4-bits Weights and Activations](https://mlsanity.com/paper/2203.13483/) (2022)
- [ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections](https://mlsanity.com/paper/2201.03013/) (2022)
- [CoNLoCNN: Exploiting Correlation and Non-Uniform Quantization for Energy-Efficient Low-precision Deep Convolutional Neural Networks](https://mlsanity.com/paper/2208.00331/) (2022)
- [Number Systems for Deep Neural Network Architectures: A Survey](https://mlsanity.com/paper/2307.05035/) (2023)
- [3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration](https://mlsanity.com/paper/2105.06250/) (2021)
- [Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization](https://mlsanity.com/paper/2306.11800/) (2023)
- [Computational Complexity Evaluation of Neural Network Applications in Signal Processing](https://mlsanity.com/paper/2206.12191/) (2022)
- [Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting](https://mlsanity.com/paper/2308.07939/) (2023)
- [BiVM: Accurate Binarized Neural Network for Efficient Video Matting](https://mlsanity.com/paper/2507.04456/) (2025)
- [Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks](https://mlsanity.com/paper/2601.16880/) (2026)
- [A Construction Kit for Efficient Low Power Neural Network Accelerator Designs](https://mlsanity.com/paper/2106.12810/) (2021)
- [Reconfigurable co-processor architecture with limited numerical precision to accelerate deep convolutional neural networks](https://mlsanity.com/paper/2109.03040/) (2021)
- [AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks](https://mlsanity.com/paper/2304.03782/) (2023)
- [Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation](https://mlsanity.com/paper/2408.02685/) (2024)
- [Evolutionary fine tuning of quantized convolution-based deep learning models](https://mlsanity.com/paper/2605.05228/) (2026)
- [Long-Term and Short-Term Transistor Aging in Deep Neural Networks: Impact and Mitigation](https://mlsanity.com/paper/2606.04266/) (2026)

## Abstract (arXiv)

High computational complexity hinders the widespread usage of Convolutional Neural Networks (CNNs), especially in mobile devices. Hardware accelerators are arguably the most promising approach for reducing both execution time and power consumption. One of the most important steps in accelerator development is hardware-oriented model approximation. In this paper we present Ristretto, a model approximation framework that analyzes a given CNN with respect to numerical resolution used in representing weights and outputs of convolutional and fully connected layers. Ristretto can condense models by using fixed point arithmetic and representation instead of floating point. Moreover, Ristretto fine-tunes the resulting fixed point network. Given a maximum error tolerance of 1%, Ristretto can successfully condense CaffeNet and SqueezeNet to 8-bit. The code for Ristretto is available.