Layer Normalization: Handwriting sequence generation

Parameters

3.7M

Published

Jul 21, 2016

Layer Normalization: Handwriting sequence generation is an AI model developed by University of Toronto (Canada), first published in July 2016. It works in the image generation domain, on tasks such as image generation.

Epoch AI has no training-compute estimate for this model. The model has 3,700,000 parameters. It was trained on roughly 8.5M datapoints.

It is built on top of RNN+weight noise+dynamic eval. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: University of Toronto
Country of organization: Canada
Domain: Image generation
Task: Image generation
Compute estimation method: Operation counting
Parameters: 3,700,000
Dataset size: 8.5M
Base model: RNN+weight noise+dynamic eval
Epoch confidence: Speculative