Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [lstm]

LSTM stands for Long Short-Term Memory. When we use this term most of the time we refer to a recurrent neural network or a block (part) of a bigger network.

1174 questions
4
votes
3 answers

What is the difference between "Adding more LSTM layers" or "Adding more units on existence layers"?

What is the difference between adding more LSTM layers and just increasing the units of existing layers? Which one is preferred and in which situation?
user3486308
  • 1,270
  • 5
  • 18
  • 28
2
votes
0 answers

What receives a LSTM neuron?

I'm confused about input data on LSTM neurons. I know that exist almost two form to give data to a recurrent neural network. I want to understand with a example Data [1,2,3,4,5,6] For feeda RNN, data must be formatted with this schema: (x,y,z) …
Extermis
  • 53
  • 6
2
votes
1 answer

What are the output shape of LSTM with "return_sequences" equal to "True" or "False"?

What are the output shape of LSTM with Keras implementation when "return_sequences" equals to "True" or "False" ?
user3486308
  • 1,270
  • 5
  • 18
  • 28
2
votes
1 answer

LSTM querying approach

I've just realized my prediction approach for LSTM might not be correct. I am trying to predict character by character, by reading over the book. The way I've approached the problem is as follows: b c …
Kari
  • 2,726
  • 2
  • 20
  • 49
2
votes
2 answers

LSTM: Taking previous output values as feature

As far as I know, there is practically no limit on the number of dimensions of input feature for LSTM. And it apparently can learn the sequence of data. My question is does LSTM by nature, also take previous output values besides feature vector as…
Alireza
  • 196
  • 1
  • 13
1
vote
3 answers

Is using LSTM correct for this?

I wish to predict whether the difference in Value and Growth returns is positive or negative for the next month. To do this, I have collected data of a few features(to be specific, Macroeconomic Indicators), and the difference in Value and Growth…
Vinayaka Srivardhan
  • 11
  • 1
1
vote
0 answers

Why is LSTM implemented in tensorflow so slow as compared to pure pythonic implementation

I am trying to implement word level prediction, an adaptation of from http://karpathy.github.io/2015/05/21/rnn-effectiveness/. When I implement it in pure python, the training is fast. However I started learning tensorflow and I tried to implement…
onexpeters
  • 11
  • 2
1
vote
0 answers

LSTM classifier for very long videos

Most videos in benchmark datasets like UCF101 are short (<40 sec) and monotonous, as in they 'focus' on a person performing a specific action (jumping, running, etc) . The whole video can be run through the ConvNet+LSTM with a logit output…
Alex
  • 767
  • 6
  • 17
1
vote
1 answer

How to design a many-to-many LSTM?

I have an input array of shape (1000,20, 4) and output(labels) of shape (1000,25,1). But don't know how to use Keras LSTM library to build a sequential model for this! Can someone help me design a simple LSTM for doing that? (I tried to use…
user3486308
  • 1,270
  • 5
  • 18
  • 28
1
vote
0 answers

Does LSTM just mocking previous data?

I am trying to do a numerical time series prediction using LSTM but it seems that the LSTM just mocking previous data(Even when I use many-to-many prediction with different lengths) and when I plot the results that I get from LSTM, I a have very…
user3486308
  • 1,270
  • 5
  • 18
  • 28
1
vote
0 answers

How does it work if we have different "time-steps" and "LSTM-units"?

As I know we can create a LSTM layer like: model.add(LSTM(units), input_shape = (time-steps, feature_number)) And the units number and time-steps number can be different numbers! So how does it work? For ex, if I specify my LSTM like…
user3486308
  • 1,270
  • 5
  • 18
  • 28
1
vote
0 answers

Predicting global horizontal irradiance using satellite images

I have the aim to build a model to predict global horizontal irradiance (ghi) using satellite images and other features namely the day of the year and time of the day. For extracting the satellite images features, I aim at using one of the available…
FenryrMKIII
  • 143
  • 8
1
vote
1 answer

GRU/LSTM models - Train/Test split

I drove myself into a corner with this, can someone please explain? I feel I'm missing something obvious... If, for LSTM, each layer is trained with inputs from t and t-1, than that'd mean that if I've got a training set of a 10 000 observations,…
HandyAndy
  • 11
  • 1
  • 2
1
vote
1 answer

Possible to correct an actual cell state in LSTM via gradient?

Why in LSTM we calculate gradient w.r.t weights, but not w.r.t the cell state? Is it theoretically possible to correct the contents of the cell state, and what would it result in? I understand that weights are like a "set of skills", so that network…
Kari
  • 2,726
  • 2
  • 20
  • 49
1
vote
1 answer

Can someone spot anything wrong with my LSTM forex model?

The model below reads in data from a csv file (date, open, high, low, close, volume), arranges the data and then builds a LSTM model trying to predict next day's close based on a number of previous days close values. However, validation accuracy is…
DBSE
  • 221
  • 2
  • 3
1
2