OPERATION OF BIDIRECTIONAL RECURRING NEURAL NETWORKS IN HARDWARE

DE602022038105T2Active Publication Date: 2026-06-10IMAGINATION TECH LTD

Patent Information

Authority / Receiving Office
DE · DE
Patent Type
Patents
Current Assignee / Owner
IMAGINATION TECH LTD
Filing Date
2022-06-29
Publication Date
2026-06-10

AI Technical Summary

Technical Problem

Implementing Bidirectional Recurrent Neural Networks (BRNNs) in hardware is challenging due to their dynamic nature, as each cell's operations depend on both forward and backward states, creating a circular dependency that is difficult to execute efficiently on accelerators designed for static neural networks.

Method used

The approach involves unrolling each BRNN cell into a pair of forward and backward recurrent neural networks over a predetermined number of timesteps, transforming the dynamic graph into a static graph suitable for implementation on conventional accelerators.

Benefits of technology

This method allows BRNNs to be efficiently executed on hardware by converting them into a static graph, enabling the same accelerators to handle both recursive and non-recursive neural networks, thereby extending their utility.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader
Need to check novelty before this filing date? Find Prior Art
No text content released.