AI models
Bidirectional RNN
Parameters
13K
Published
Nov 1, 1997
Bidirectional RNN is an AI model developed by Advanced Telecommunications Research Institute (Japan), first published in November 1997. It works in the speech domain, on tasks such as speech recognition (asr).
Epoch AI has no training-compute estimate for this model. The model has 13,000 parameters. It was trained on roughly 142.9K datapoints.
The reference paper has 7,990 citations.
Full record
- Organization
- Advanced Telecommunications Research Institute
- Country of organization
- Japan
- Domain
- Speech
- Task
- Speech recognition (ASR)
- Parameters
- 13,000
- Dataset size
- 142.9K
- Citations
- 7,990
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models