Skip to main content

Table 4 Results for 1-of-70, 1-of-256, log-70 and log-256

From: Improving deep neural network design with new text data representations

Embedding Alphabet size Time per Epoch Accuracy
log-m 70 13.5s 73.106
256 13.5s 74.945
1-of-m 70 65.5s 69.845
256 77.7s 69.748
  1. Best results in italic