Questions tagged [sequence]
The sequence tag has no usage guidance.
53
questions with no upvoted or accepted answers
3
votes
3
answers
123
views
Classification when the classification of the previous itens matter
I have a classification problem to solve, that seems to be common but I am struggling to find the name of this task and the best way to model this problem.
Suppose I have a series of events that are ...
- 31
3
votes
1
answer
109
views
User actions sequence classification
I have a training set where each row is a series of user actions on a website (logged in, sent an invoice, etc.) and times deltas in ms between these actions. Each row has a label — a corresponding ...
3
votes
2
answers
3k
views
Running out of memory when training Keras LSTM model for binary classification on image sequences
I'm trying to come up with a Keras model based on LSTM layers that would do binary classification on image sequences.
The input data has the following shape: ...
- 131
3
votes
0
answers
296
views
Why embedding or rnn/lstm can not handle variable length sequence?
Pytorch embedding or lstm (I don't know about other dnn libraries) can not handle variable-length sequence by default. I am seeing various hacks to handle variable length. But my question is, why this ...
- 521
3
votes
0
answers
1k
views
TypeError: unsupported operand type(s) for %: 'int' and 'NoneType'(Stateful LSTM Keras)
So I have a trained LSTM model with which I am trying to predict future values. The model is stateful as seen below
...
- 149
3
votes
0
answers
185
views
Next events prediction based on previous events
I have data set of sequences of user executed commands sorted in the order of its occurrence. The data looks like this.
...
- 31
2
votes
0
answers
118
views
1D Sequence Classification
Cross-post from https://stackoverflow.com/questions/71752744/1d-sequence-classification
I am working with a long sequence (~60 000 timesteps) classification task with continuous input domain. The ...
- 163
2
votes
1
answer
22
views
How to use time-sequence data with "meta data" of single value per sample?
I'm, trying to estimate a fish weight by a time-sequence signal of the change in resistance when the fish goes through a gate with electrodes installed.
When the fish pass through the gate there's a ...
- 23
2
votes
1
answer
43
views
Comapring hidden markov models
Given a set of sequence transitions, there are different orders of hidden markov models that can be fitted to a dataset.
Is there any test to determine which is the best model for a given sequence ...
- 21
2
votes
1
answer
194
views
What's an appropriate datastore for variable length sequence data for PyTorch consumption?
I have a large number of sequences - potentially hundreds of thousands - each consisting of between 100 and 10,000 items, which each consist of about 5 floats.
I need a datastore that can rapidly ...
- 121
2
votes
0
answers
679
views
Proper loss function for sequence prediction model with multi-step output
Consider a typical time series (sequence) prediction problem that use previous $k$ step historical features to predict the next step target. We use RNN model as an ...
- 515
2
votes
1
answer
540
views
Sequence models word2vec
I am working a data-set with more than 100,000 records. This is how the data looks like:
...
- 21
2
votes
0
answers
68
views
Mapping “event” series, with segments of variable length, to time series for loss calculation
I have a time series of data which I map to a time series of non-exclusive binary features (in my case, short-time audio spectrograms to features of the audio). I will refer to a collection of these ...
- 140
2
votes
0
answers
83
views
Classifying sequences of mouse clicks with different number of clicks per sequence
I have a series of sequences, each sequence contains multiple mouse click with the following features: [x coordinate on screen, y coordinate on screen, duration of click], and each sequence is labeled ...
- 121
2
votes
0
answers
478
views
k- means clustering on Markov chain trasition probability
I have data set of 50 students. I want to cluster them on their sequential data ( While doing a job they followed multiple sequences A, B, c total 7 stages). I am planning to apply k-means clustering ...
2
votes
0
answers
83
views
Classifying Sequences Where Some Sequences in Both Classes
I am building a modified RNN (specifically a GRU) to classify sequences. These sequences are of variable length, and contain "states". Each point in the sequence is categorical and they look like [A,B,...
- 21
2
votes
2
answers
204
views
Modeling the influence of events order on probability
The case is to model if the sequence of events influences the probability of binary target variable. We have for example five different events which occur in time (event: A,B,C,D,E). They can occur in ...
- 31
1
vote
0
answers
16
views
Techniques for early binary classification from sequences revealed over time in a low data environment?
We have data with objects, each of which has a series of events. A series is 1-50 events, revealed over time (a few months). These objects have events come in at different times during a season, so ...
- 123
1
vote
0
answers
37
views
Forecasting on multivariate time series containing quaternions
I have a multivariate time series containing 3D position data ($x,y,z)$ and orientation data (as quaternions) obtained from motion sensors.
My goal is to forecast the future position/orientation, and ...
- 111
1
vote
1
answer
13
views
What is the formal category of problem described by identifying consecutive occurrences of attributes in records?
Apologies for the garbled title, I'd really need to know the answer to the question before I could phrase it properly...
Let's imagine I've got a data set of football(soccer if you prefer) match ...
1
vote
0
answers
36
views
1
vote
0
answers
80
views
How to compare different forecasting models over different time horizon?
Developed multiple Models with AR, ARIMA, VAR; LSTM , SARIMA.
Now, the purpose is to find out which model performs best on a given use case with different time horizons.
The time series data is ...
1
vote
0
answers
444
views
How does data shuffling work when LSTM is involved?
TIL that when using the LSTM layer, the states are remembered throughout the same batch. When using stateful LSTM, they can be even remembered outside of the batch.
The first realization gave me a ...
- 201
1
vote
0
answers
38
views
Text generation with deep neural network?
For my master's project, I have to build a deep learning model for text generation: the model learns on a set of sentences, then it generates new sentences based on those from which it learned.
I ...
- 11
1
vote
1
answer
176
views
Handle with very short and very long sequences with Neural Network
I am working on multi-class problem with sequences. My dataset is composed of sequences of data with different length.
E.g. 1500 labeled samples: 500 datapoint belongs to class A, 500 class B and 500 ...
- 11
1
vote
1
answer
43
views
How can I predict the last element of the fixed length=8 sequence after I get each element?
There are fixed length lists [X1, X2, X3, X4, X5, X6, X7, X8] like this.
I have many lists like them from the past. In the future, I will get new element of current list on weekly bases. one new ...
1
vote
0
answers
107
views
Create sequence for a Conv1D layer
Im studying the following tutorial on the Keras website and I'm trying to understand how to create a sequence for a Conv1D layer.
This is their method:
...
- 53
1
vote
0
answers
121
views
Machine learning for circular sequences
My data are sequences of real numbers $a_0,a_1,...,a_{n-1}$. The length of a sequence is fixed and equals $n$. Each sequence is mapped to a real number $y$ and I want to predict $y$ given the sequence....
- 1,096
1
vote
0
answers
18
views
What is External representation of time in Sequential learning?
I am reading the literature on sequential learning and it is often mention that in order to handle sequential/temporal data, there two categories of work in sequential learning
External ...
- 316
1
vote
0
answers
31
views
Long sequence prediction with model trained on short sequence
I'll start with a specific example.
I would like to train model which predict vector of [0-1]. Values close to 1 on specific range indicates that in those timesteps is particular activation word (...
- 161
1
vote
0
answers
39
views
Time Series Forecasting with RNN/LSTM/NARX
I have some experimental datasets (like 4 or 5), and each dataset has three time series data, say $u1(t)$, $u2(t)$, and $x(t)$. The three time series of each experiment are similar but not the same. ...
- 11
1
vote
0
answers
26
views
What is the problem classification (e.g. sequence-to-sequence) for prediction of an autocorrelated sequence from multiple autocorrelated sequences?
I will try to provide a simple example to illustrate my question. I have training data for many oil wells. The training data consists of the well identifier, a timestamp, other relevant properties ...
- 11
1
vote
0
answers
49
views
Optimizing ad placement using historical data
Edit: increased generality.
I have an ad placement optimization problem and I am brainstorming to determine which ML techniques are well suited to it.
Basically, I have some objective that involves ...
- 254
1
vote
0
answers
1k
views
Code or Package to cluster sequences (or time series) of different lengths based on HMM?
Is there any existing code or packages in Python, R, Java, Matlab, or Scala that implements the sequence clustering algorithms in any of the following 2 papers?
1) 'Clustering Sequences with Hidden ...
- 111
1
vote
0
answers
927
views
Sequence Embedding
Is there a way to get embedding for an ordered sequence of vectors?
I want to get embeddings to feed them further into net i.e. train it to arbitrary loss function simultaneously for embeddings and ...
- 11
1
vote
0
answers
94
views
How do I separate Interleaved sentences using LSTM networks?
I have a problem statement wherein the following input
The James world Bond shall can't end save us tomorrow.
must be converted into this -
The world shall end tomorrow
&
James Bond can't ...
1
vote
0
answers
657
views
RNN sequence length and cell size
I am trying to build a RNN model to classify time series.
My time series data consist of numbers with length 200.
I am using tensorflow, and when i create the placeholder for the data it is like this:...
- 323
1
vote
1
answer
287
views
Clustering sequences of sentence embeddings
I have a sequence of events, right now I am not worried about their actual times, just the order. This is a sequence of web page views.
I have modelled my data as the following, where each element ...
- 120
0
votes
0
answers
6
views
Are the filtering problem and decoding problem the same thing?
Is there any distinction the filtering problem and the decoding problem?
Wikipedia's definition for a filtering problem is:
The problem of estimating the states or ideally the posterior distribution ...
0
votes
0
answers
31
views
Improving Wake-Word Detection Model Performance: Seeking Advice and Suggestions
I was assigned a task to train a wake-word detection model. Basically, it's a binary sequence classification model on audio samples where it should be 1 if it recognizes the wake word being said (e.g. ...
- 71
0
votes
0
answers
16
views
Conditional density estimation for sequences using conditional random fields
I am looking to estimate the conditional distribution of the next observation $x_{t+1} \in \mathbb{R}_+$ of a discrete-time process, given the current observation and $l$ previous observations. I am ...
- 1
0
votes
0
answers
24
views
Why use sliding window input features in deep learning?
I was reading through the DNABERT paper and found that their input features were k-mers. This is equivalent to using rolling/sliding window features in the other common family of sequential problem, ...
- 131
0
votes
1
answer
41
views
Why would a sequence-model vs n-gram model depending on ratio of Samples / Words per Sample
This ML tutorial from Google is analyzing the imdb reviews dataset to predict the tag positive or negative. When choosing a model
Calculate the number of samples/number of words per sample ratio.
If ...
- 393
0
votes
1
answer
32
views
Sequence prediction in Parent - Child dataset
We have a large collection of documents (D), each accompanied by a set of metadata (M). Within this collection, some documents act as parent documents and have multiple child documents. Both parent ...
- 101
0
votes
0
answers
88
views
LSTM multivariate time-series with categorical, numerical and non-temporal inputs
I have a dataset that contains different data types and I'm working on a prediction task of dataset features with LSTM network, but I'm struggling in finding the right way to construct the neural ...
- 1
0
votes
1
answer
202
views
How is PCA applied to (one-hot encoded) DNA sequence data?
I realize some questions have been asked already about one-hot encoding for PCA. The answer seems to be along the lines of 'The PCA will run, but does not necessarily make sense.'
However, I have a ...
- 51
0
votes
0
answers
19
views
Selecting an element in a sequence with self-attention networks
I have a doubt on I should set up the following problem:
Data:
My data is a tensor with shape (N, J, F) where N is the batch size, J is the sequence length, and F is the number of features of each ...
0
votes
0
answers
19
views
Many To One LSTM - Can I Use the Same Sequence as Input from Previous Timesteps?
I'm new to LSTMs, and I'm trying to do a basic timeseries prediction using stock prices. However, I'm a bit confused as to how the LSTM is supposed to remember outputs from previous timesteps when it ...
- 101
0
votes
1
answer
39
views
Classification of sequential data
I'm currently trying to classify discrete sequential data into five classes with machine learning.
The setup is the following:
The actual object is filled with various properties, but to separate the ...
- 21
0
votes
1
answer
38
views
Deep Learning Model to predict sum of Sequences based on flag value
I am trying to Predict Sum of the Sequence based on flag but my model is not able to converge.
for each time stamp, include the first element in sum if second number is 1 in
Sequence.
Example
...
