metadata
library_name: keras
language: en
datasets: newsgroup
tags:
- multiclass-classification
- newsgroup
Model description
Text classification on the Newsgroup20 dataset using pre-trained GloVe word embeddings.
This repo contains the model to this Keras example using pre-trained word embeddings.
Full credits to : fchollet
Model reproduced by : Sumedh
Training and evaluation data
Newsgroup20 dataset, a set of 20,000 message board messages belonging to 20 different topic categories
Training hyperparameters
The following hyperparameters were used during training:
| name | learning_rate | decay | rho | momentum | epsilon | centered | training_precision |
|---|---|---|---|---|---|---|---|
| RMSprop | 0.0010000000474974513 | 0.0 | 0.8999999761581421 | 0.0 | 1e-07 | False | float32 |
Model Plot
View Model Plot
