BP-DBN

Parameters

18M

Published

Jan 1, 2009

BP-DBN is an AI model developed by University of Toronto (Canada), first published in January 2009. 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 18,030,592 parameters. Training ran on 1 NVIDIA Tesla S1070.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: University of Toronto
Country of organization: Canada
Domain: Speech
Task: Speech recognition (ASR)
Parameters: 18,030,592
Training hardware: NVIDIA Tesla S1070
Chips used: 1
Training power draw: 984 W
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident