# Learning Recurrent Binary/Ternary Weights

arXiv: https://arxiv.org/abs/1809.11086 · HTML: https://mlsanity.com/paper/1809.11086/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2018.

## Built on by (most cited first, 9 of 9)

- [A Survey on Model Compression for Large Language Models](https://mlsanity.com/paper/2308.07633/) (2023)
- [4-bit Quantization of LSTM-based Speech Recognition Models](https://mlsanity.com/paper/2108.12074/) (2021)
- [Training Integer-Only Deep Recurrent Neural Networks](https://mlsanity.com/paper/2212.11791/) (2022)
- [iRNN: Integer-only Recurrent Neural Network](https://mlsanity.com/paper/2109.09828/) (2021)
- [Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Models](https://mlsanity.com/paper/2104.07951/) (2021)
- [Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization](https://mlsanity.com/paper/2206.07882/) (2022)
- [Quantized Approximately Orthogonal Recurrent Neural Networks](https://mlsanity.com/paper/2402.04012/) (2024)
- [HadamRNN: Binary and Sparse Ternary Orthogonal RNNs](https://mlsanity.com/paper/2502.00047/) (2025)
- [SSR: Sparse Segment Reduction for Ternary GEMM Acceleration](https://mlsanity.com/paper/2610.08403/) (2026)

## Abstract (arXiv)

Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile devices requiring real-time processes with limited hardware resources. To address the above issues, we introduce a method that can learn binary and ternary weights during the training phase to facilitate hardware implementations of RNNs. As a result, using this approach replaces all multiply-accumulate operations by simple accumulations, bringing significant benefits to custom hardware in terms of silicon area and power consumption. On the software side, we evaluate the performance (in terms of accuracy) of our method using long short-term memories (LSTMs) on various sequential models including sequence classification and language modeling. We demonstrate that our method achieves competitive results on the aforementioned tasks while using binary/ternary weights during the runtime. On the hardware side, we present custom hardware for accelerating the recurrent computations of LSTMs with binary/ternary weights. Ultimately, we show that LSTMs with binary/ternary weights can achieve up to 12x memory saving and 10x inference speedup compared to the full-precision implementation on an ASIC platform.