AI models
Fuzzy NN
Training compute
1.4×10⁹ FLOP
Parameters
1.2K
Published
Sep 1, 1992
Fuzzy NN is an AI model developed by Indian Statistical Institute (India), first published in September 1992. It works in the speech domain, on tasks such as speech recognition (asr).
Training it took an estimated 1.4×10⁹ FLOP of compute (estimation method: operation counting). The model has 1,166 parameters. It was trained on roughly 436 datapoints.
The reference paper has 1,223 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Indian Statistical Institute
- Country of organization
- India
- Domain
- Speech
- Task
- Speech recognition (ASR)
- Training compute
- 1.4×10⁹ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 1,166
- Dataset size
- 436
- Citations
- 1,223
- Epoch confidence
- Confident
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