AI models
LSTM+NeuralCache
Training compute
9.8×10¹⁴ FLOP
Parameters
2.1M
Published
Sep 24, 2018
LSTM+NeuralCache is an AI model developed by KU Leuven, ESAT - PSI and Apple (Belgium and United States), first published in September 2018. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 9.8×10¹⁴ FLOP of compute (estimation method: operation counting). The model has 2,100,000 parameters. It was trained on roughly 2M datapoints.
Access: Unreleased. Its weights are not openly released. The reference paper has 3 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- KU Leuven, ESAT - PSI, Apple
- Country of organization
- Belgium, United States
- Domain
- Language
- Task
- Language modeling
- Training compute
- 9.8×10¹⁴ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 2,100,000
- Dataset size
- 2M
- Numerical format
- FP32
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 3
- Epoch confidence
- Likely
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