I'm seeing a rather strange phenomenon in training an LSTM on a time series.
I'm training it on early data and testing on later data. After say 100 epochs
the test data produces lower error than the train data. This could just be a
coincidence, but since the test data is about 25% of a total dataset of about
1200 cases, it still seems kind of strange.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/Tbd9e6404771d6b20-M2c6dbde57c746032a10e7777
Delivery options: https://agi.topicbox.com/groups/agi/subscription
