All Questions
6 questions
19
votes
2
answers
3k
views
Showing machine learning results are statistically irrelevant
This is a question as part of a paper review which was already published. The authors of the paper publish $R^2$ and RMSE in training but only RMSE in validation. Utilizing the published code, $R^2$ ...
- 315
0
votes
0
answers
238
views
Time series data validation error is significantly lower than training error
I have a time series dataset that covers daily observations (closing price) for several stocks, and I would like to build models to forecast the closing prices for the future 7 days using their ...
- 1
1
vote
0
answers
36
views
Tests for predictive models with autoregressive neural networks
I'm working with time series predictions with NNAR autoregressive neural network models (p, P, k) and I'm doubtful for the validation of my models. After making the predictions, I'm selecting those ...
- 111
0
votes
1
answer
112
views
What is a good way to test a bidirectional recurrent neural network?
I wrote an implementation of a bidirectional RNN. How can I verify that this implementation is correct by using a small dataset?
Is there any simple test that compares performance of bidirectional ...
- 121
0
votes
1
answer
2k
views
Best Validation accuracy occurs early on in the training process
I am working with time series and exploring two dimensional representations to train them using a CNN. The current 2D representation is 256 X 256. I have used ResNet-50, InceptionResnetV2 and another ...
8
votes
2
answers
6k
views
What is a good way to test a simple Recurrent Neural Network
I have coded up a simple real-value regression RNN in theano.
What kind of dataset should I test it on?
How should I go about testing it?
My structure is:
Univariate (for now) timeseries, $x_{in}(...
