AI models
Hybrid CNN/SVM Object Categorizer
Training compute
9.8×10¹³ FLOP
Parameters
3.6M
Published
Jun 17, 2006
Hybrid CNN/SVM Object Categorizer is an AI model developed by Courant Institute of Mathematical Sciences (United States), first published in June 2006. It works in the vision domain, on tasks such as object recognition and image classification.
Training it took an estimated 9.8×10¹³ FLOP of compute (estimation method: operation counting). The model has 3,590,057 parameters. It was trained on roughly 291.6K datapoints.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Courant Institute of Mathematical Sciences
- Country of organization
- United States
- Domain
- Vision
- Task
- Object recognition, Image classification
- Training compute
- 9.8×10¹³ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 3,590,057
- Dataset size
- 291.6K
- Training time
- 52 h
- Model accessibility
- Unreleased
- Open weights
- No
- Epoch confidence
- Confident
More from Courant Institute of Mathematical Sciences
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