All Questions
12 questions
1
vote
2
answers
1k
views
Extracting embeddings of categorical features back to original data frame in Python
Suppose I have a dataframe with several numerical variables and 1 categorical variable with 10000 categories. I use a neural network with Keras to get a matrix of embeddings for the categorical ...
- 633
2
votes
1
answer
5k
views
How to concatenate embeddings with variable length inputs in Keras?
Here is the network diagram I am working on and data is tabular and structured,
On the left, we have some abilities which are continuous features and on the right, we could have 'N' number of ...
- 846
2
votes
1
answer
134
views
Dealing with multiple categorical inputs and variable-sized groups as inputs to neural network
I'm working with data which consists of numerical and categorical features, where each input consists of a variable-sized group of the features.
For example: predict the price of a house by using ...
2
votes
1
answer
714
views
Using ELMo with Keras, how to correctly input the training set and labels?
so I am trying to use Elmo with Keras, I used this Elmo code since it the only trainable one Elmo
Using this Elmo, the embedding is integrated as a layer following the input layer, so the input layer ...
- 720
1
vote
1
answer
1k
views
Combine text with categorical features using entity embeddings and Keras functional API
I'm trying to combine text and categorical variables using Keras functional API.
The model compiles but when I try to train the model using "fit", it gives me an error.
Looks like the way I put the ...
- 31
1
vote
0
answers
235
views
Implementing a GloVe embedding layer into Keras model
I am looking at creating a siamese network in which the format of the code I am using follows the keras Model instantiation seen here Keras API
I am having trouble trying to implement an Embedding ...
- 75
6
votes
2
answers
6k
views
Keras Layer Concatenation
I'm trying to see how I can create a model in Keras with multiple Embedding Layers and other inputs. Here's how my model is structured(E=Embedding Layer, [....]=Input Layer):
E E [V V V]
\ | /
\...
- 375
6
votes
2
answers
5k
views
Keras seq2seq - word embedding
I am working on a generative chatbot based on seq2seq in Keras. I used code from this site: https://machinelearningmastery.com/develop-encoder-decoder-model-sequence-sequence-prediction-keras/
My ...
- 151
15
votes
4
answers
8k
views
Keras embedding layers: how do they work?
I am starting using Keras to build neural networks models.
I have a classification problem, where the features are discrete.
To manage this case, the standard procedure consists in converting the ...
- 1,068
3
votes
1
answer
2k
views
Apply a shared Embedding layer on a set of documents in keras
I am trying to create a model in which I want to predict the order of a certain set of documents given a certain query. My idea was basically to use a shared embedding layer for both the query and the ...
- 2,539
2
votes
1
answer
1k
views
How to replace an Embedding layer with a Time Distributed Dense after training?
I have the following problem:
I want to use a LSTM network for text classification. In order to speed up training and make code more clear I want to use an Embedding layer along keras.Tokenizer in ...
- 40.4k
10
votes
2
answers
10k
views
How to use the Embedding Layer for Recurrent Neural Network (RNN) in Keras
I'm rather new to Neural Networks and the Keras Library and I'm wondering how I can use the Embedding Layer as described here to mask my input data from a 2D tensor to a 3D tensor for a RNN.
Say my ...
- 1,385