While I am training, it seems like my Loss is going down, but my Accuracy remains constant throughout training. It always seems to go towards 0.0023 no matter how I tweak my network and input data length etc.

I am pretty new in this field so any help would be appreciated :)

My input data is a sequence (seq_length) of sample levels before a current sample level. So basically predict the current sample level based on the previous (seq_length).

Network is Sequential: Dense(seq_length) LSTM(seq_length*10) Dense(1)

Validation set is 0.33 of the total input samples

Using Tensorflow Keras on Windows

CSV of loss,accuracy,val loss etc: https://pastebin.com/GPsmeUmg

While I am training, it seems like my loss is going down, but my accuracy remains constant throughout training. It always seems to go towards 0.0023 no matter how I tweak my network, input data length, etc.

My input data is a sequence of sample levels before a current sample level. So basically predict the current sample level based on the previous sample levels.

Network is Sequential:

Dense(seq_length) LSTM(seq_length*10) Dense(1) 

Validation set is 0.33 of the total input samples.

Using Tensorflow Keras on Windows.

CSV of loss, accuracy, val loss, etc: https://pastebin.com/GPsmeUmg

While I am training, it seems like my Loss is going down, but my Accuracy remains constant throughout training. It always seems to go towards 0.0023 no matter how I tweak my network and input data length etc.

I am pretty new in this field so any help would be appreciated :)

My input data is a sequence (seq_length) of sample levels before a current sample level. So basically predict the current sample level based on the previous (seq_length).

Network is Sequential: Dense(seq_length) LSTM(seq_length*10) Dense(1)

Validation set is 0.33 of the total input samples

CSV of loss,accuracy,val loss etc: https://pastebin.com/GPsmeUmg

While I am training, it seems like my Loss is going down, but my Accuracy remains constant throughout training. It always seems to go towards 0.0023 no matter how I tweak my network and input data length etc.

I am pretty new in this field so any help would be appreciated :)

My input data is a sequence (seq_length) of sample levels before a current sample level. So basically predict the current sample level based on the previous (seq_length).

Network is Sequential: Dense(seq_length) LSTM(seq_length*10) Dense(1)

Validation set is 0.33 of the total input samples

Using Tensorflow Keras on Windows

CSV of loss,accuracy,val loss etc: https://pastebin.com/GPsmeUmg