'In RNN, I am unable to understand how time steps are mapped to the Output shape

In Simple RNN Layer, number of units corresponds to the output shape specification. If unrolled, each time steps can be represented as a separate layer.

But I am unable to understand how this is mapped to the output shape. Here in the example: SimpleRNN(16, input_shape(1600,1), activation='relu'). How 1600 time steps are mapped producing 16 units?

deep-learninglstmrecurrent-neural-networkbias-neurongru


Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source

Related Questions

Tensorflow LSTM/GRU reset states once per epoch and not for each new batch

making GRU/LSTM states trainable in Tensorflow/Keras and add some random noise

LSTM/GRU setting states to random noise instead or resetting to zero

AttributeError: module 'tensorflow.python.pywrap_tensorflow' has no attribute 'TFE_Py_RegisterExceptionClass'

How does calculation in a GRU layer take place

which algorithm does google keyboard uses for automatic suggestions (personal vocab included)?

logits and labels must be broadcastable error in Tensorflow RNN

Tensorflow-addons seq2seq - start and end tokens in BaseDecoder or BasicDecoder

PCA for Recurrent Neural Networks (LSTM) - Shall I use PCA for target variables too?

I'm using Gradio for making UI for my model

Tensorflow error: ValueError: Shapes (128, 100) and (128, 100, 139) are incompatible

How to setup LSTM to use n-grams instead of sequence length?

Difference between hidden dimension and n_layers in rnn using pytorch

Custom GRU model (OGRU)

Is there a way to get the real sequence_length in the model description of a RNN/LSTM in Keras?