Questions tagged [gated-recurrent-unit]

For questions related to the gated recurrent unit (GRU), a modification and simplification of the LSTM unit, which is a more sophisticated unit (with respect to the standard one) of a recurrent neural network (RNN). An RNN that uses GRU units is often called a GRU network. GRUs were introduced in the paper "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation" (2014) by Kyunghyun Cho et al.

Filter by
Sorted by
Tagged with
0
votes
0answers
37 views

Seq2Seq Modelling: when implementing some machine translation net, how are special tokens embedded?

When implementing any encoder-decoder network for machine translation, during training we provide the true output sentence to the decoder so that the context vector (from source language) may be ...
2
votes
0answers
37 views

Can One-Hot Vectors be used as Inputs for Recurrent Neural Networks?

When using an RNN to encode a sentence, one normally takes each word, passes it through an embedding layer, and then uses the dense embedding as the input into the RNN. Lets say instead of using dense ...
1
vote
0answers
163 views

What is the computational complexity in terms of Big-O notation of a Gated Recurrent Unit Neural network?

I have been digging up of articles across the internet in context of computational complexity of GRU. Interestingly, I came across this article, http://cse.iitkgp.ac.in/~psraja/FNNs%20,RNNs%20,LSTM%...
3
votes
0answers
83 views

What is the time complexity for training a gated recurrent unit (GRU) neural network using back-propagation through time?

Let us assume we have a GRU network containing $H$ layers to process a training dataset with $K$ tuples, $I$ features, and $H_i$ nodes in each layer. I have a pretty basic idea how the complexity of ...
0
votes
0answers
31 views

Time series forecast for everyday for till a distant future

I have time series data for every single day from last 5 years with seasonal variation and a general increase in trend. This is what my data looks like: And I am trying to predict for every single ...
2
votes
0answers
37 views

Incorporating domain knowledge into recurrent network

I am currently trying to solve a classification task with a recurrent artificial neural network (RNN). Situation There are up to 350 inputs (X) mapped on one categorical output (y)(13 differnt ...
3
votes
1answer
137 views

What's the difference between LSTM and GRU?

I have been reading about LSTMs and GRUs, which are recurrent neural networks (RNNs). The difference between the two is the number and specific type of gates that they have. The GRU has an update gate,...
1
vote
1answer
26 views

Inner working of Bidirectional RNNs

I'm trying to understand how Bidirectional RNNs work. Specifically, I want to know whether a single cell is used with different states, or two different cells are used, each having independent ...
4
votes
0answers
124 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 ...
2
votes
1answer
549 views

How do I choose the size of the hidden state of a GRU?

I'm trying to understand how the size of the hidden state affects the GRU. For example, suppose I want to make a GRU count. I'm gonna feed it with three numbers, and I expect it to predict the ...
4
votes
2answers
139 views

Why are GRU and LSTM better than standard RNNs?

It seems that older RNNs have a limitation for their use cases and have been outperformed by other recurrent architectures, such as the LSTM and GRU.