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.

Filter by
Sorted by
Tagged with
52
votes
4answers
86k views

How to select number of hidden layers and number of memory cells in an LSTM?

I am trying to find some existing research on how to select the number of hidden layers and the size of these of an LSTM-based RNN. Is there an article where this problem is being investigated, i.e., ...
37
votes
3answers
32k views

Why does the transformer do better than RNN and LSTM in long-range context dependencies?

I am reading the article How Transformers Work where the author writes Another problem with RNNs, and LSTMs, is that it’s hard to parallelize the work for processing sentences, since you have to ...
17
votes
1answer
426 views

Could a Boltzmann machine store more patterns than a Hopfield net?

This is from a closed beta for AI, with this question being posted by user number 47. All credit to them. According to Wikipedia, Boltzmann machines can be seen as the stochastic, generative ...
16
votes
2answers
306 views

How do I decide the optimal number of layers for a neural network?

How do I decide the optimal number of layers for a neural network (feedforward or recurrent)?
13
votes
4answers
12k views

Where can I find the original paper that introduced RNNs?

I was able to find the original paper on LSTM, but I was not able to find the paper that introduced "vanilla" RNNs. Where can I find it?
13
votes
1answer
3k views

How can Transformers handle arbitrary length input?

The transformer, introduced in the paper Attention Is All You Need, is a popular new neural network architecture that is commonly viewed as an alternative to recurrent neural networks, like LSTMs and ...
13
votes
3answers
4k views

What is the relationship between the size of the hidden layer and the size of the cell state layer in an LSTM?

I was following some examples to get familiar with TensorFlow's LSTM API, but noticed that all LSTM initialization functions require only the num_units parameter, ...
12
votes
2answers
3k views

What is a recurrent neural network?

Surprisingly, this wasn't asked before - at least I didn't find anything besides some vaguely related questions. So, what is a recurrent neural network, and what are their advantages over regular (or ...
12
votes
1answer
5k views

Which approaches could I use to create a simple chatbot using a neural network?

I wanted to start experimenting with neural networks, so I decided to make a chatbot (like Cleverbot, which is not that clever anyway) using them. I looked around for some documentation and I found ...
11
votes
5answers
8k views

What is the fundamental difference between CNN and RNN?

What is the fundamental difference between convolutional neural networks and recurrent neural networks? Where are they applied?
11
votes
4answers
1k views

What are the models that have the potential to replace neural networks in the near future?

Are there possible models that have the potential to replace neural networks in the near future? And do we even need that? What is the worst thing about using neural networks in terms of efficiency?
10
votes
4answers
780 views

Are we technically able to make, in hardware, arbitrarily large neural networks with current technology?

If neurons and synapses can be implemented using transistors, what prevents us from creating arbitrarily large neural networks using the same methods with which GPUs are made? In essence, we have ...
8
votes
2answers
1k views

Why use a recurrent neural network over a feedforward neural network for sequence prediction?

If recurrent neural networks (RNNs) are used to capture prior information, couldn't the same thing be achieved by a feedforward neural network (FFNN) or multi-layer perceptron (MLP) where the inputs ...
7
votes
1answer
771 views

Is LSTM a subcategory of RNN?

Is the LSTM-Architecture a subcategory of RNNs? Or are they totally different? Literature doesn't seem to be unitary on this. This figure appears to explain the models to be alternatives, but I ...
7
votes
2answers
261 views

How to design a neural network when the number of inputs is variable?

I'm looking to design a neural network that can predict which runner wins in a sports game, where the number of runners varies between 2-10. In each case, specific data about the individual runners (...
7
votes
1answer
1k views

A mathematical explanation of Attention Mechanism

I am trying to understand why attention models are different than just using neural networks. Essentially the optimization of weights or using gates for protecting and controlling cell state (in ...
7
votes
2answers
452 views

What are the best machine learning models for music composition?

What are the best machine learning models that have been used to compose music? Are there some good research papers (or books) on this topic out there? I would say, if I use a neural network, I would ...
6
votes
2answers
422 views

Which machine learning algorithm could I use to break up a poem by lines?

I want to create a network to predict the break up of poetry lines. The program would receive as input an unbroken poem, and would output the poem broken into lines. For example, an unbroken poem ...
6
votes
3answers
176 views

In sequence-to-sequence, why is the output of the decoder used as its input?

The basic seq-2-seq model consists of 2 parts: a recurrent encoder that compresses a sequence to a vector and decoder that unrolls the vector into the output sequence: Why is the output, ...
6
votes
3answers
2k views

How should we regularize an LSTM model?

There are five parameters from an LSTM layer for regularization if I am correct. To deal with overfitting, I would start with reducing the layers reducing the hidden units Applying dropout or ...
5
votes
4answers
3k views

How can I predict the next number in a non-obvious sequence?

I've got an array of integers ranging from -3 to +3. Example: [1, 3, -2, 0, 0, 1] The array has no obvious pattern since it represents bipolar disorder mood swings. What is the most suitable approach ...
5
votes
4answers
8k views

What exactly is a hidden state in an LSTM and RNN?

I'm working on a project, where we use an encoder-decoder architecture. We decided to use an LSTM for both the encoder and decoder due to its hidden states. In my specific case, the hidden state of ...
5
votes
2answers
177 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.
5
votes
1answer
3k views

What exactly are the "parameters" in GPT-3's 175 billion parameters and how are they chosen/generated?

When I studied neural networks, parameters were learning rate, batch size etc. But even GPT3's ArXiv paper does not mention anything about what exactly the parameters are, but gives a small hint that ...
5
votes
1answer
110 views

Are neurons instantly feed forward when input arrives?

Let's say I have a neural network with 5 layers, including the input and output layer. Each layer has 5 nodes. Assume the layers are fully connected, but the 3rd node in the 2nd layer is connected to ...
5
votes
1answer
112 views

Why do small datasets require more samples, while big datasets require fewer samples in negative sampling?

In the deep learning specialization course by Andrew Ng, in the video Sequence Models (minute 4:13), he says that in negative sampling we have to choose a sample of words from the corpus to train ...
5
votes
1answer
721 views

Over- and underestimations of the lowest and highest values in LSTM network

I'm training an LSTM network with multiple inputs and several LSTM layers in order to set up a time series gap filling procedure. The LSTM is trained bidirectionally with "tanh" activation ...
5
votes
1answer
62 views

Is there any relation between the recursive neural network and recurrent neural network?

Recurrent neural networks, abbreviated as RNNs, are widely used in deep learning literature, especially for text processing. Are they related to recursive neural networks in any way? I am asking for ...
5
votes
2answers
920 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) ...
4
votes
2answers
118 views

Do convolutional neural networks also have recurrent connections? [duplicate]

I asked my self this simple question while reading "Comment Abuse Classification with Deep Learning" by Chu and Jue. Indeed, they say at the end of the that It is clear that RNNs, specifically ...
4
votes
1answer
398 views

Why do feedforward neural networks require the inputs to be of a fixed size, while RNNs can process variable-size inputs?

Why does a vanilla feedforward neural network only accept a fixed input size, while RNNs are capable of taking a series of inputs with no predetermined limit on the size? Can anyone elaborate on this ...
4
votes
1answer
1k views

How can I understand this statement about RNNs and hidden layers?

In the lecture, there was a statement: Recurrent neural networks with multiple hidden layers are just a special case that has some of the hidden to hidden connections missing. I understand ...
4
votes
1answer
79 views

Why RNNs often use just one hidden layer?

Did I get it right, that RNNs most often have just one hidden neuron layer? Is there a reason for that? Will RNNs with several hidden layers in each cell work worse? Thank you!!
4
votes
2answers
463 views

Are there neural networks that accept graphs or trees as inputs?

As far I know, the RNN accepts a sequence as input and can produce as a sequence as output. Are there neural networks that accept graphs or trees as inputs, so that to represent the relationships ...
4
votes
1answer
442 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,...
4
votes
1answer
53 views

Training an RNN to answer simple quesitons

I would like to train an RNN to follow the sentences: "Would you like some cheese"? with "Yes, I would like some cheese." So whenever the template "Would you like some ____?" appears then RNN ...
4
votes
1answer
61 views

How to graphically represent a RNN architecture implemented in Keras?

I'm trying to create a simple blogpost on RNNs, that should give a better insight into how they work in Keras. Let's say: ...
4
votes
0answers
91 views

Why Pixel RNN (Row LSTM) can capture triangular contexts?

I'm reading the paper Pixel Recurrent Neural Network. I have a question about Row LSTM. Why Row LSTM can capture triangular contexts? In this paper, the kernel of the one-dimensional convolution ...
4
votes
0answers
167 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
0answers
89 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 ...
4
votes
1answer
214 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 The Unreasonable Effectiveness of Recurrent Neural Networks) that when training RNN on text for something like language modeling, the text is usually featurized character-by-...
3
votes
2answers
171 views

How do layers in an artificial neural network transform inputs to outputs?

To me, most ANN/RNN related articles don't tell me actually how the network is implemented. I know that in the ANN you'll have multiple neurons, activation function, weights, etc. But, how do you, ...
3
votes
1answer
66 views

Is there a common way to build a neural network that seeks to extract spatial and temporal information simultaneously?

Is there a common way to build a neural network that seeks to extract spatial and temporal information simultaneously? Is there an agreed up protocol on how to extract this information? What ...
3
votes
1answer
127 views

Any comparison between transformer and RNN+Attention on the same dataset?

I am wondering what is believed to be the reason for superiority of transformer? I see that some people believe because of the attention mechanism used, it’s able to capture much longer dependencies. ...
3
votes
1answer
107 views

How to use text as an input for a neural network - regression problem? How many likes/claps an article will get

I am trying to predict the number of likes an article or a post will get using a NN. I have a dataframe with ~70,000 rows and 2 columns: "text" (predictor - strings of text) and "likes&...
3
votes
2answers
421 views

How can active learning be used in the case of complex models that require a lot of data?

We have a series of data and we want to label the parts of each series. As we do not have any training data, we could try to use active learning as a solution, but the problem is that our classifier ...
3
votes
1answer
913 views

What is a state in a recurrent neural network?

I am Reading "Supervised Sequence Labelling with Recurrent Neural Networks" written by Alex Graves to try to understand LSTM networks and I am a bit confused about the equations. Specifically, what I ...
3
votes
1answer
39 views

In a Temporal Convolutional Network, how is the receptive field different from the input size?

I'm playing around with TCN's lately and I don't understand one thing. How is the receptive field different from the input size? I think that the receptive field is the time window that TCN considers ...
3
votes
1answer
241 views

What is teacher forcing?

In the paper Neural Programmer-Interpreters, the authors use the teacher forcing technique, but what exactly is it?
3
votes
1answer
788 views

How does the CTC loss work?

I am trying to implement CTC loss in TensorFlow, but their documentation is pretty limited. So I am not sure how to approach the problem. I found a good example in Theano. Are any other resources that ...

1
2 3 4 5
7