Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Deep-deep neural network language models.

More »

Fig 1 Expand

Table 1.

Details of n-gram vocabularies from the MCI and AD-type dementia datasets.

More »

Table 1 Expand

Table 2.

Percentages of transcript files for training, test, and validation sets for the MCI and AD-type dementia datasets.

More »

Table 2 Expand

Table 3.

% error and perplexity on MCI held-out test set.

(h = Hidden layer size; Bz = Batch size).

More »

Table 3 Expand

Table 4.

% error and perplexity on AD-type dementia held-out test set (h = Hidden layer size; Bz = Batch size).

More »

Table 4 Expand

Fig 2.

% Error of the D2NNLMs vs. DNNLM on MCI dataset with smaller number of hidden layers.

More »

Fig 2 Expand

Fig 3.

% Error of the D2NNLMs vs. DNNLM on AD-type dementia dataset with smaller number of hidden layers.

More »

Fig 3 Expand

Fig 4.

Perplexity comparison between the D2NNLMs and DNNLM on the MCI dataset with smaller number of hidden layers.

More »

Fig 4 Expand

Fig 5.

Perplexity comparison between the D2NNLMs and DNNLM on the AD-type dementia dataset with smaller number of hidden layers.

More »

Fig 5 Expand

Table 5.

Performance comparison with the LPOCV AUC on the MCI dataset, N = 38.

More »

Table 5 Expand

Table 6.

Performance comparison with the LPOCV AUC on the AD-type dementia dataset, N = 198.

More »

Table 6 Expand