Tag for questions about Multi layer perceptrons (MLP). It is a class of feedforward artificial neural network. Multilayer perceptrons are sometimes colloquially referred to as "vanilla" neural networks, especially when they have a single hidden layer
Questions tagged [mlp]
275 questions
14
votes
6 answers
With BERT Text Classification, ValueError: too many dimensions 'str' error occuring
Trying to make a classifier for sentiments of texts with BERT model but getting ValueError : too many dimensions 'str'
That is the DataFrame for values of train data; so they are train_labels
0 notr
1 notr
2 notr
3 negative
4 notr
...…
KazımTibetSar
- 141
- 1
- 1
- 3
11
votes
1 answer
Using Tensorflow 2.0 and eager execution without Keras
So this question might stem from a lack of knowledge about tensorflow. But I am trying to build a multilayer perceptron with tensorflow 2.0, but without Keras.
The reason being that it is a requirement for my machine learning course that we do not…
Anders Stendevad
- 111
- 1
- 3
6
votes
1 answer
How to feed Bert embeddings to LSTM
I am working on a Bert + MLP model for text classification problem. Essentially, I am trying to replace the MLP model with a basic LSTM model.
Is it possible to create a LSTM with embedding? Or, is best to create a LSTM with embedded layer?
More…
Green
- 695
- 2
- 9
- 21
5
votes
0 answers
How to visualize model training history using scikit learn's MLP classifier?
I have used the pima-indians-diabetes.csv dataset. I have built a neural network containing architecture 12-8-1 using Keras and I was able to visualize the training history perfectly. Next, I tried to implement the same model using MLPCLassifier…
Faria Zarin Subah 1504027
- 103
- 2
- 12
5
votes
2 answers
Tuning MLPRegressor hyper parameters
I have been trying to tune hyper parameters of a MLP model to solve a regression problem but I always get a convergence warning.
This is my code
def mlp_model(X, Y):
estimator=MLPRegressor()
param_grid = {'hidden_layer_sizes': [(50,50,50),…
Y. Gopee
- 113
- 1
- 1
- 10
4
votes
1 answer
Error when checking input: expected dense_1_input to have 2 dimensions, but got array with shape (25000, 700, 50)
trainData.shape = (25000, 700, 50) , Shape as follows:
[[[ 0.7095 0.863 0.712 ... 0.02715 -1.305 0.5195 ]
[-0.66 1.715 -1.934 ... 0.5684 0.754 0.2593 ]
[-0.3533 2.256 -1.292 ... -0.2708 0.6714 -1.128 ]
...
…
user9903583
- 53
- 1
- 4
4
votes
1 answer
Google Colab TPU takes more time than GPU
Below is the code I am using. I commented out the line to convert my model to the TPU model. With GPU for the same amount of data it's taking 7 seconds for an epoch while using TPU it takes 90 secs.
Inp = tf.keras.Input(name='input',…
mihirjoshi
- 12,161
- 7
- 47
- 78
3
votes
2 answers
Why don't LogisticRegression and MLPClassifier produce the same results?
A neural network with no hidden layers and sigmoid/softmax activation is just logistic regression:
from sklearn.datasets import load_iris
from sklearn.neural_network import MLPClassifier
from sklearn.linear_model import LogisticRegression
X, y =…
invictus
- 1,821
- 3
- 25
- 30
3
votes
1 answer
Fluentbit - parsing log with multiple format (log+json)
I'm trying to send to elasticsearch the following log line through fluentbit, but I didn't find the right solution to extract both time and the json structure after the [MLP] part:
2020-12-29 08:00:03,230 INFO [http-nio-3410-exec-7]…
Meekly
- 31
- 2
3
votes
3 answers
MLP with Scikitlearn: Artificial Neural Network application for forecast
I have traffic data and I want to predict number of vehicles for the next hour by showing the model these inputs: this hour's number of vehicles and this hour's average speed value.
Here is my code:
dataset=pd.read_csv('/content/final -…
B. Selin Zaza
- 91
- 4
3
votes
1 answer
Error when trying to tune MLPClassifier hidden_layer_sizes using BayesSearchCV
When trying to tune the sklearn MLPClassifier hidden_layer_sizes hyper parameter, using BayesSearchCV, I get an error: ValueError: can only convert an array of size 1 to a Python scalar.
However, when I use GridSearchCV, it works great! What am I…
onofricamila
- 930
- 1
- 11
- 20
3
votes
2 answers
MLPRegressor working but results don't make any sense
I am building a neural network with my research data in two ways: with a statistical programm (SPSS) and with python.
I am using the scikit learn MLPRegressor. The problem I have is that whereas my code is , apparently, well written (because it…
Covadonga Palacio
- 35
- 1
- 5
3
votes
1 answer
AttributeError: 'MLPClassifier' object has no attribute 'best_loss_'
I was experimenting with the warm_start parameter in scikit-learn's MLPClassifier. However, I received an error while running the following code.
clf = MLPClassifier(solver='adam',
hidden_layer_sizes=(128, 128),
…
Benjamin Lee
- 31
- 1
- 4
3
votes
1 answer
How does sklearn's MLP predict_proba function work internally?
I am trying to understand how sklearn's MLP Classifier retrieves its results for its predict_proba function.
The website simply lists:
Probability estimates
While many others, such as logistic regression, have more detailed answers:
Probability…
artemis
- 6,857
- 11
- 46
- 99
3
votes
0 answers
K Fold Cross validation in MLP
I want to implement the cross validation in the MLP Regressor in my data set. I want to know if my code is correct or not? Is this the way to cross validate? Here is my sample data:
Wavelength Phase_velocity Shear_wave_velocity
1.50 …
Sadia Mitu
- 89
- 6