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.

Filter by
Sorted by
Tagged with
1
vote
0answers
269 views

speech accent recognition data augmentation and training

I am using a Kaggle dataset to learn more about using sound with Deep Learning. I have extracted the mfcc features using this cool library - librosa. However, I want to try feature extraction ...
4
votes
1answer
3k views

Kalman filter for time series prediction

I have the information about the behaviour of 400 users across period of 1 months (30 days). Across those 30 days I measure 4 different information (let's call it A,B,C and D), hence I have a total of ...
2
votes
0answers
403 views

LSTMs: BPTT vs RTRL in training

In the 2000 paper that originally described the modern LSTM (Gers et al.), the training algorithm is described as follows: Output units use BPTT; output gates use slightly, modified, truncated BPTT....
7
votes
1answer
8k views

Multiple output for multi step ahead prediction using LSTM with keras

I am new to deep learning and LSTM (with keras). I am trying to solve a multi-step ahead time series prediction. I have 3 time series: A, B and C and I want to predict the values of C. I am training ...
6
votes
1answer
6k views

The model of LSTM with more than one unit

In stacked LSTM, for example: 2 LSTM layers, LSTM_1 in order to pass the output of every time step to LSTM_2, so it needs to return hidden state value in every time step, like the architecture I drew ...
29
votes
1answer
11k views

Time Series prediction using LSTMs: Importance of making time series stationary

In this link on Stationarity and differencing, it has been mentioned that models like ARIMA require a stationarized time series for forecasting as it's statistical properties like mean, variance, ...
0
votes
2answers
2k views

Keras: LSTM unit nums vs timesteps

I am using Keras LSTM (Tensorflow backend) to fit a time series model. Here is my model: ...
2
votes
2answers
251 views

Using LSTM to clear up corrupted text files

LSTM can be used to generate text, can they be used to fix corrupted text files? Say that my original was: ...
0
votes
1answer
1k views

Character-based word representation using bi-lstm

In this blog, it teaches us how to get a word embedding using bi-lstm in character level like the image below: I am wondering how to optimize the word vector from character-based approach. Is there ...
6
votes
1answer
7k views

Is it necessary to perform rolling-window on LSTMs?

Let's say I have a set of n time-series with sequence length 8 [[a,b,c,d,e,f,g,h],[f,e,g,r,g,h,e,a],[a,e,r,a,k,e,l,i],...,[e,r,q,g,l,r,p,q]] And let's define the input that LSTM expects as a ...
17
votes
4answers
14k views

Prediction interval around LSTM time series forecast

Is there a method to calculate the prediction interval (probability distribution) around a time series forecast from an LSTM (or other recurrent) neural network? Say, for example, I am predicting 10 ...
1
vote
0answers
51 views

Input data from time series, keeping part of the steps to predict

I am using Keras LSTM for time series forecasting. I am facing an issue, with transforming my data correctly. I have a big dataset with values as follows [[x1,x2,x3,x4,x5,x6,x7,x8], [x1,x2,x3,x4,x5,...
2
votes
1answer
215 views

Creating an easy but not trivial dataset

I am working on the problem of automatic punctuation: given a stream of words, decide for each word whether there should be a punctuation mark after it (in future work I also want to distinguish ...
2
votes
1answer
120 views

Using LSTMs for modelling and forecasting several time series generated by the same process

My scenario is roughly the following: Imagine 500 cars, all Toyota Corollas (or whatever). While these cars have many similarities, they are not exactly identical: some of them have 1.5 liter engines ...
-1
votes
1answer
2k views

LSTM with multiple entries per time step

I have a dataset with sales numbers for around 100 related products. Every day, the number of sales of each product is recorded along with other relevant information (what day of the week is it, is it ...
2
votes
1answer
675 views

LSTM Validation MSE always lower than Train MSE

I am trying to train a LSTM network to forecast time steps further. I have a list of queries and the current question is based on one among them. The validation loss (using mse) is always lower than ...
2
votes
2answers
7k views

LSTM - How many times should I look back to predict next six hours -Multivariate Time-Series

I am still finding confusing on look back topic when using LSTM for time-series analysis. If I have hourly data and I want to predict next 6 hours with multiple ...
17
votes
3answers
12k views

Advantages of stacking LSTMs?

I'm wondering in what situations it is advantageous to stack LSTMs?
2
votes
2answers
1k views

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 ...
6
votes
2answers
25k views

Value Error: Operands could not be broadcast together with shapes - LSTM

I am trying an LSTM model using tensorflow following this tutorial . I am having trouble understanding why am I getting an ...
10
votes
1answer
7k views

How to use Embedding() with 3D tensor in Keras?

I have a list of stock price sequences with 20 timesteps each. That's a 2D array of shape (total_seq, 20). I can reshape it into ...
5
votes
2answers
8k views

Time series forecasting with RNN(stateful LSTM) produces constant values

I have a time series daily data for about 6 years(1.8k data points). I am trying to forecast the next t+30 values, Train data independent matrix (X)=Sequences of previous 30 day values Train (Y)=The ...
2
votes
1answer
1k views

Stock Price Data Manipulation for LSTM

I am trying to construct a machine learning model that predicts the difference in price from tomorrow to the day after tomorrow, using yesterday's OHLCV (open, high, low, close, volume). My models (...
2
votes
3answers
2k views

Multi-Source Time Series Data Prediction

I was wondering if anyone has experience with time series prediction for data from multiple sources. So for instance, time series $a,b,..,z$ each have their own shape, some may be correlated with ...
1
vote
1answer
618 views

LSTM text generation

Most of the examples I have found online for LSTMs refer to "random" text generation. One of the problems that I'm trying to solve is to generate a "summary" of many docs into 1 doc. For example: ...
4
votes
3answers
2k views

Handwritting Recognition moving from character level to word level

Given the experience on MIST, I try this problem as a character level. I have a handwritten text and I want to "OCR" it. Even though I made progresses with openCV (on the image pre-processing, ...
160
votes
6answers
151k views

When to use GRU over LSTM?

The key difference between a GRU and an LSTM is that a GRU has two gates (reset and update gates) whereas an LSTM has three gates (namely input, output and forget gates). Why do we make use of GRU ...

1
17 18 19 20
21