Variations in LSTM Accuracy Due to Shuffled Feature Columns

6 次查看（过去 30 天）
Hamza
Hamza 2023-11-11
编辑： Hamza 2023-11-24
Hello everyone, I applied LSTM to speech emotion recognition and achieved an accuracy of 42.1709%. However, when I shuffled the columns "features," the accuracy changed to 42.4925%. This variance is unexpected because I used the same data with only the columns shuffled. I attempted to use gpurng and rng to preserve the accuracy without success. Could someone please assist me? The code used is attached below. To shuffle the matrix, uncomment the lines: appp = appp(:, t(1:end)); testt = testt(:, t(1:end)).
  10 个评论
显示 8更早的评论
Hamza
Hamza 2023-11-13
@Walter Roberson I totally agree with you. Is there a method to extract the weights, then shuffle them as shuffled data? I think this way will solve the issue!
Sam Schumacher
Sam Schumacher 2023-11-13
I think this slight change in accuracy is to be expected.
When you freeze the weights, but shuffle the features relative to those weights, the optimisation process starts by activating the layers using different values. The weights and data are mapped differently once columns shuffled.
if possible, re-order the weights after creating the neural network, according to the way you shuffled the columns. This way the initial weights multiply by the same values in the dataset before begging the backpropogation

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品


版本

R2023b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by