AI models
Predictive Coding NN
Training compute
1.9×10¹³ FLOP
Parameters
206.9K
Published
Dec 2, 1994
Predictive Coding NN is an AI model developed by Technical University of Munich (Germany), first published in December 1994. It works in the language domain, on tasks such as language modeling. It counts among the frontier models: the systems trained with the most compute of their moment.
Training it took an estimated 1.9×10¹³ FLOP of compute (estimation method: operation counting). The model has 206,910 parameters. It was trained on roughly 600K datapoints.
Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Technical University of Munich
- Country of organization
- Germany
- Domain
- Language
- Task
- Language modeling
- Training compute
- 1.9×10¹³ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 206,910
- Dataset size
- 600K
- Epoch confidence
- Confident
More from Technical University of Munich
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