RNN (SGD+CLR)

Closed weights University of Montreal / Université de Montréal 195.6K parameters December 2012

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
University of Montreal / Université de Montréal
Organisation type
Academia
Country
Canada
Published
14 December 2012
Authors
Yoshua Bengio, Nicolas Boulanger-Lewandowski and Razvan Pascanu

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Audio
Task
Language modeling, Audio generation

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
195.6K

It uses 400 hidden units (selected via hyperparameter tuning) The input size is 88 (corresponding to the 88 piano pitches) It uses rectified linear units, so no activation function parameters So the number of parameters would be: Input to hidden weights: 88 * 400 = 35,200 Hidden to hidden weights: 400 * 400 = 160,000 Biases: 400 Total: ~195,600 parameters Above estimate is by Claude 2. Should be checked manually.

Training data
tokens

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Speculative
Citations
647

Sources

Where this record came from and when it was last checked.

Reference
Advances in Optimizing Recurrent Networks
Last updated
11 February 2026

What the numbers mean

What this model is

RNN (SGD+CLR) was published by University of Montreal / Université de Montréal, in the country recorded as Canada, during December 2012. It comes out of an organisation categorised as academia.

It works in the domain of Audio, and is recorded as performing the task of language modeling, Audio generation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Answers

RNN (SGD+CLR) — common questions

01

RNN (SGD+CLR)— what is it used for?

It works in the domain of Audio, and is recorded as handling the task of language modeling, Audio generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

RNN (SGD+CLR)— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

03

RNN (SGD+CLR)— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

04

RNN (SGD+CLR)— how many parameters does it have?

It has a parameter count of 195.6K. It uses 400 hidden units (selected via hyperparameter tuning) The input size is 88 (corresponding to the 88 piano pitches) It uses rectified linear units, so no activation function parameters So the number of parameters would be: Input to hidden weights: 88 * 400 = 35,200 Hidden to hidden weights: 400 * 400 = 160,000 Biases: 400 Total: ~195,600 parameters Above estimate is by Claude 2. Should be checked manually. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

05

RNN (SGD+CLR)— who created it?

It was published by University of Montreal / Université de Montréal, based in Canada, an organisation categorised as academia.

06

RNN (SGD+CLR)— when was it released?

It was published in December 2012. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 11 February 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.