# Fixed-Point Performance Analysis of Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1512.01322 · HTML: https://mlsanity.com/paper/1512.01322/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2015.

## Built on by (most cited first, 10 of 10)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Patch-wise Mixed-Precision Quantization of Vision Transformer](https://mlsanity.com/paper/2305.06559/) (2023)
- [SPIQ: Data-Free Per-Channel Static Input Quantization](https://mlsanity.com/paper/2203.14642/) (2022)
- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)
- [PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models](https://mlsanity.com/paper/2306.00014/) (2023)
- [Reduced-Order Neural Network Synthesis with Robustness Guarantees](https://mlsanity.com/paper/2102.09284/) (2021)
- [Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization](https://mlsanity.com/paper/2607.06922/) (2026)
- [ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models](https://mlsanity.com/paper/2105.03176/) (2021)
- [Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization](https://mlsanity.com/paper/2105.01868/) (2021)
- [Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting](https://mlsanity.com/paper/2608.12259/) (2026)

## Abstract (arXiv)

Recurrent neural networks have shown excellent performance in many applications, however they require increased complexity in hardware or software based implementations. The hardware complexity can be much lowered by minimizing the word-length of weights and signals. This work analyzes the fixed-point performance of recurrent neural networks using a retrain based quantization method. The quantization sensitivity of each layer in RNNs is studied, and the overall fixed-point optimization results minimizing the capacity of weights while not sacrificing the performance are presented. A language model and a phoneme recognition examples are used.