# When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference

> Source: <https://aiflash.com/news/114845/>
> Published: 2026-09-07 02:30:38+00:00

Quantization is widely used to reduce the computational and memory demands of neural-network inference. In recurrent networks, however, the quantized state is stored and returned at the next time step, so the rule used to store that state can alter subsequent computations. Here, we introduce recurre