mlsanityData to 7 Oct 2026

Hardware-oriented Approximation of Convolutional Neural Networks

arXiv 1604.03168 ↗First posted 11 Apr 2016cs.CVcited by 20

Not on the map. Why?

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 5; 2024: 1; 2025: 1; 2026: 3.

20 papers.

Sort:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  3. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  4. 2022SPIQ: Data-Free Per-Channel Static Input Quantizationcited by 12
  5. 2022MKQ-BERT: Quantized BERT with 4-bits Weights and Activationscited by 10
  6. 2022ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connectionscited by 4
  7. 2022CoNLoCNN: Exploiting Correlation and Non-Uniform Quantization for Energy-Efficient Low-precision Deep Convolutional Neural Networkscited by 4
  8. 2023Number Systems for Deep Neural Network Architectures: A Surveycited by 4
  9. 20213U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Accelerationcited by 3
  10. 2023Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantizationcited by 2
  11. 2022Computational Complexity Evaluation of Neural Network Applications in Signal Processingcited by 1
  12. 2023Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgettingcited by 1
8 more
  1. 2025BiVM: Accurate Binarized Neural Network for Efficient Video Mattingcited by 1
  2. 2026Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attackscited by 1
  3. 2021A Construction Kit for Efficient Low Power Neural Network Accelerator Designscited by 0
  4. 2021Reconfigurable co-processor architecture with limited numerical precision to accelerate deep convolutional neural networkscited by 0
  5. 2023AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networkscited by 0
  6. 2024Artificial Neural Networks for Photonic Applications: From Algorithms to Implementationcited by 0
  7. 2026Evolutionary fine tuning of quantized convolution-based deep learning modelscited by 0
  8. 2026Long-Term and Short-Term Transistor Aging in Deep Neural Networks: Impact and Mitigationcited by 0