Questions tagged as 'redes-neuronales'

1
answer

Neural network with backward propagation returns the same outputs for large vectors

I have a problem with the neural network of backward propagation, it is written in Python , here I leave the GitHub link (in English), with a vector of 4096 entries, 2 hidden layer neurons and 197 output neurons. I put the network to...
asked by 12.09.2016 / 23:26
0
answers

How to transform an MLP neural network into an RNN?

I have an MLP rating to predict the prices of the stock market prediction [0:] and the sentiment score on the 'sentiment_score' items. Now I want to try an RNN to do the same. However, I cook during the adjustment. The MLP classifier was: f...
asked by 22.12.2018 / 12:58
1
answer

test neural network library

I was testing the library link , this is my code var synaptic = require('synaptic'); // this line is not needed in the browser var A = synaptic.Neuron(); var B = synaptic.Neuron(); A.project(B); A.activate(0.5); // 0.5 B.activate(); // 0.3244...
asked by 23.11.2016 / 15:12
1
answer

I can not execute Tensor Flow

I want to train my own neural network but I can not execute the example. I execute the following command: python classify_image.py And I get the following:    Traceback (most recent call last): File "classify_image.py", line   46, in    ...
asked by 16.04.2017 / 19:17
0
answers

Error: Input arrays should have the same number of samples as target arrays.Found 6400 input samples and 1600 target samples

I'm trying to do classification but I have this error import os,cv2 import numpy as np from sklearn.utils import shuffle from tensorflow.python.keras.preprocessing.image import ImageDataGenerator from sklearn.model_selection import train_test_...
asked by 26.10.2018 / 23:11
0
answers

Is Tensorflow not compatible with all PCs?

I feel like I'm dealing with an internal TensorFlow error. I am trying to replicate the convoluted neuronal network developed by David Shahrestani for the Kaggle classification competition for toxic comments. Clonolo on Github here . I hav...
asked by 12.03.2018 / 19:03