Questions tagged [recurrent-neural-networks]

For questions related to recurrent neural networks (RNNs), artificial neural networks that contain backward or self-connections, as opposed to just having forward connections, like in a feed-forward neural network. An RNN can be trained using back-propagation through time, such that these backward connections "memorize" previously seen inputs. Consequentially, RNNs are well suited to sequence prediction and similar tasks.

82 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4
votes
0answers
49 views

RNN models displays upper limit on predictions

I have trained a RNN, GRU, and LSTM on the same dataset, and looking at their respective predictions I have observed, that they all display an upper limit on the value they can predict. I have ...
4
votes
1answer
195 views

dimensions of hidden layer and cell state layer in LSTM

I was following some examples to get familiar with tensorflow LSTM related api, but noticed that all LSTM initialization functions require only num_units parameter which denotes number of hidden units ...
3
votes
0answers
16 views

How to back propagate for implementation of Sequence-to-Sequence with Multi Decoders

I am proposing a modified version of Sequence-to-Sequence model with dual decoders. The problem that I am trying to solve is Neural Machine Translation into two languages at once. This is the ...
3
votes
0answers
26 views

What evaluation metric are used for sequence-to-sequence prediction problems?

I am solving many sequence-to-sequence prediction problems using RNN/LSTM. What type of evaluation metrics can be used for sequence prediction problems? One metric is the mean squared error (MSE) ...
3
votes
0answers
39 views

Ideas on a network that can translate image differences into motor commands?

I'd like to design a network that gets two images (an image under construction, and an ideal image), and has to come up with an action vector for a simple motor command which would augment the image ...
3
votes
1answer
46 views

How are the observations stored in the RNN that encodes the state?

I am a bit confused about observations in RL systems which use RNN to encode the state. I read a few papers like this and this. If I were to use a sequence of raw observations (or features) as an ...
3
votes
0answers
106 views

How does bidirectional encoding allow the predicted word to indirectly “see itself”?

Before the release of BERT, we used to say that it is not possible to train bidirectional models by simply conditioning each word on its previous and next words, since this would allow the word that's ...
3
votes
0answers
42 views

How do the relative number of cells between neighboring stacked LSTM layers affect the network's behavior?

It seems that stacking LSTM layers can be beneficial for some problem settings in order to learn higher levels of abstraction of temporal relationships in the data. There is already some discussion on ...
3
votes
0answers
98 views

What is the intuition behind the calculation of the similarity between encoder and decoder states?

Suppose that we are doing machine translation. We have a conditional language model with attention where we are are trying to predict a sequence $y_1, y_2, \dots, y_J$ from $x_1, x_2, \dots x_I$: $$P(...
3
votes
0answers
97 views

Why are all the actions converging to the same index?

I am using PPO with an LSTM agent. My agent is performing 10 actions for each episode, one action is corresponding to one LSTM timestep and the action space is discrete. I have only one reward per ...
3
votes
0answers
128 views

Training RNN's on text: Can you use an ASCII encoding just as well as a one-hot character encoding?

I've mostly seen (e.g. in http://karpathy.github.io/2015/05/21/rnn-effectiveness/) that when training RNN's on text for something like language modeling, the text is usually featurized character-by-...
2
votes
0answers
13 views

How do I train a multiple-speaker model (speech synthesis) based on Tacotron 2 and espnet?

I'm new to Speech Synthesis & Deep Learning. Recently, I got a task as described below: I have problem in training a multi-speaker model which should be created by Tacotron2. And I was told I can ...
2
votes
0answers
21 views

How do I determine the best neural network architecture for a problem with 3 inputs and 12 outputs?

This post continues the topic in the following post: Is it possible to train a neural network with 3 inputs and 12 outputs?. I conducted several experiments in MATLAB and selected those neural ...
2
votes
0answers
44 views

Is there a recurrent neural network where the output becomes a partial input?

I am aware of the way RNN works (finite and infinite impulse) and I have seen a lot of use (e.g. in speech recognition). I have understood it is used to "store" value and/or re-use them. But I am ...
2
votes
0answers
21 views

How are batch statistics computed in Recurrent Batch Normalization?

I'm implementing recurrent BN per this paper in Keras, but looking at it and those citing it, a detail remains unclear to me: how are batch statistics computed? Authors omit explicit clarification, ...
2
votes
0answers
33 views

Difference in the code structure of RNN and CNN

I understand that in general RNN is good for time series data and CNN image data, and have noticed many blogs explaining the ...
2
votes
0answers
59 views

What is a location-based addressing in a neural Turing machine?

In the neural Turing machine (NTM), the content-based addressing and location-based addressing is used for memory addressing. Content-based addressing is similar to the attention-based model, ...
2
votes
0answers
40 views

How can my Neural Network categorize message strings?

Abstract I wish to design a neural network that will categorize messages based on criteria I have predefined. It should feature the ability to be proactively trained as it continues its lifecycle. ...
2
votes
0answers
97 views

Update of weights in Recurrent Neural Network through back propagation

How does Recurrent Neural Network updates its weights and bias through backpropagation? Is time taken into account while updating the weights of a RNN using Backpropagation through time(BPTT)?"
2
votes
0answers
99 views

Combine two embeddding inputs to increase more performance in LSTM model

The situation I encountered here is that I have two inputs(for instance, image embedding, etc.) into the first lstm of a series of lstms to predict the next word to generate sentence(from the second ...
2
votes
0answers
37 views

Detecting symmetry in small images with RNN

My network works on 32x32 normalized (translationally) but noisy images. Its task it to determine whether image has simple symmetry (horizontal/vertical). It needs to be reasonably robust to rotation (...
2
votes
0answers
46 views

Recommendations on which architecture to use to guess appointment

I'm currently developping an application which allows psychologists to manage their schedule and budget. As a proof of concept, I would like to create an intelligent appointment service. There can be ...
2
votes
0answers
50 views

Are gradients of weights in RNNs dependent on the gradient of every neuron in that layer?

I am writing my own recurrent neural network in Java to understand the inner workings better. While working through the math, I found that in timesteps later than 2 the gradient of weight w of neuron ...
2
votes
0answers
67 views

seq2seq vector to letters model

I'm looking to build a sequence-to-sequence model that takes in a 2048-long vector of 1s and 0s as my input and translating it to my known output of (a variable length) 1-20 long characters (ex. ...
2
votes
0answers
143 views

Preprocessing of training dataset for machine learning

I'm developing a log analyzer to predict and find errors in an equipment. Each logged data contains the following format: ...
2
votes
2answers
290 views

What is the significance of this Stanford University “Financial Market Time Series Prediction with RNN's” paper?

Researchers at Stanford University released this paper in 2012: http://cs229.stanford.edu/proj2012/BernalFokPidaparthi-FinancialMarketTimeSeriesPredictionwithRecurrentNeural.pdf It goes on to ...
1
vote
0answers
3 views

How to pad the output sequence during training for an encoder decoder model

I've got an encoder-decoder model for character level English language spelling correction, it is pretty basic stuff with a two LSTM encoder and another LSTM decoder. However, up until now, I have ...
1
vote
0answers
7 views

Recurrent neural Network for survival analyses: Dealing with forecast data as feature which can exceed the number of days untill a event occurs

I am building a Recurrent Neural network (LSTM) for predicting the number of days until a Pollen season starts (when the cumulative of the year exceeds X). One of the features I am including in my ...
1
vote
1answer
29 views

What’s the difference between LSTM and RNN?

What's the difference between LSTM and RNN? I know that RNN is a network layer used in neural networks, but what exactly is an LSTM? Is it also a network layer with the same characteristics?
1
vote
0answers
13 views

When stacking LSTM's, should the hidden units increase?

I'm using Weights and Biases to do some hyperparameter sweeping for a supervised sequence-to-sequence problem I'm working on. One thing I noticed is that the sweeps with a gradually increasing number ...
1
vote
0answers
20 views

What is the difference between an generalised estimating equation and a recurrent neural network?

What is the difference between a generalised estimating equation (GEE) model and a recurrent neural network (RNN) model, in terms of what these two models are doing? Apart from the differences in the ...
1
vote
0answers
12 views

Simple sequential model with LSTM which doesn't converge

I'm actually trying to create a sequential neural network in order to translate a "human" sentence in a "machine" sentence understandable by an algorithm. Like It didn't work, I've try to create a NN ...
1
vote
1answer
10 views

how to produce documents like factset blackline?

factset blackline reports essentially can compare two 10-Q SEC filings and show you the difference between the two documents. It highlights added items in green and removed items in red + ...
1
vote
0answers
30 views

Can GraphRNN be used with very large graphs?

In the GraphRNN paper, the authors only implement the algorithm up to a graph size of 2k nodes. Would this still work on much larger graphs (on the order of $10^7$)? Or would the computation just ...
1
vote
1answer
14 views

What is the appropriate RNN structure to do Sentiment Analysis with multiple dependent ratings?

Suppose we are doing sentiment analysis for a restaurant. Customers can rate the restaurant by #1: how expensive the restaurant is, #2:how good is the food and #3: how likely they will come again. The ...
1
vote
0answers
14 views

Is there a way to use RNN (in tensorflow) to do something like a batch Kalman with the weight dynamics specified in the loss?

Or would you simply do this as a time series of models. Basically I think you can think of time series of weights as the hidden states and the dynamics driving the weight time series as the RNN ...
1
vote
0answers
30 views

How to exploit translational symmetry for extrapolation in video generation using machine learning

I'll try to rephrase my problem in the context of video processing. Imagine that initial frame of video has some translational symmetry. The frame evolves according to an update rule. I generate a ...
1
vote
0answers
10 views

How do I build a multi RNN network with keras?

I have 2 (independently long) sequences (a and b) of feature vectors that I want to use as input for a neural network. The idea was to build 2 GRU based encoders (one for each sequence). I would than ...
1
vote
0answers
21 views

What is the term for an RNN that is a completely connected directed graph?

There seems to be a severe problem with the taxonomy of neural network topologies. What I'd like to know is the term I should use to search for the most general topology: completely connected ...
1
vote
0answers
25 views

Imposing contraints on sequence of image classifications

Are there example implementations of networks that apply constraints across sequences of image classifications where class labels are ordinal numbers? For example, to cause the output of a CNN to ...
1
vote
0answers
31 views

What is the correct input shape for my LSTM network?

My professor gave us a workshop where we have to do classification of a dataset of ECG signals between healthy and unhealthy types using LSTM. Each signal consists of 1,285 time steps. What my prof ...
1
vote
0answers
23 views

Is there an standard algorithm for giving options from an RNN?

You can feed books to an RNN and it learn how to produce text. What I'm interested in is an algorithm that, given say 20 letters it suggest, say the best 10 options for the next 10 letters. So for ...
1
vote
0answers
20 views

Literature on Sequence Regresssion

I have some rated time-sequential data and I would like to test if an ANN can learn a correlation between my measurements and ratings. I suspect I could just try a CNN where 1 Dimension is time or an ...
1
vote
0answers
14 views

A gated neural network for internal thought?

I have an idea for an RNN which has no separate internal memory state only an output. But there is a gate in which tells the neural network whether the output will be acted out in the physical world ...
1
vote
0answers
32 views

Dynamic frames processing with CNN LSTM combination or otherwise

I have a unique implementation where I have to process videos with dynamic frame rates (that is the number of frames is different for each video in a batch). I am stacking all the frames in a single ...
1
vote
1answer
67 views

How can I stabilise a recurrent neural network used for binary classification?

I’m looking for some help with my neural network. I’m working on a binary classification on a recurrent neural network that predicts stock movements (up and down) Let’s say I’m studying Eur/Usd, I’m ...
1
vote
0answers
43 views

RNN weights when varying the input size

I have a time-varying input size vector for a RNN. However, I am facing some difficulties understanding how to deal with my network weights when the input changes. Say we have a set of natural ...
1
vote
0answers
16 views

Using the cloud service to trasform a picture using a neural algorithm?

yesterday I tried to transform a picture in the artistic style using CNNs based on A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge using a recent Torch ...
1
vote
0answers
38 views

What is the feasible neural network structure that can learn to identify types of trajectory of moving dots?

I have multiple image sequences, each of which contains an animation of two moving dots. The trajectory of the dots in a sequence is always cyclic (not necessarily circular). There are two types of ...
1
vote
2answers
100 views

Which algorithm should I use to map an input sentence to an output sentence?

I am new to NLP realm. If you have an input text "The price of orange has increased" and output text "Increase the production of orange". Can we make our RNN model to predict the output text? Or what ...