Network structure inspired by simplified models of biological neurons (brain cells). Neural networks are trained to "learn" by supervised and unsupervised techniques, and can be used to solve optimization problems, approximation problems, classify patterns, and combinations thereof.

**0**

votes

**0**answers

9 views

### dplyr: Mutate call throwing deep “Evaluation Error”

I'm working on a dataset of pokemon (download)(web-link). I'm attempting to turn a column of categorical variables into an int vector representation in preparation for creating a neural network. My ...

**0**

votes

**0**answers

13 views

### Wide and deep neural network - Why is the loss fluctuating?

I'm trying to train a wide and deep neural network (https://www.tensorflow.org/tutorials/wide_and_deep) with my own dataset.My dataset features are numeric values. It has many columns (280) and it is ...

**-1**

votes

**0**answers

6 views

### expected dense_1_input to have shape (1,) but got array with shape (3072,)

I am Newbie for this topic. I am learning about neural network to encourage my career. So, when I was learning from one of the website, I got this code (below) to try out. When I run this in my ...

**0**

votes

**0**answers

11 views

### GAN Generator output layer is [way] out of target range - potentially due to loss func

The TL;DR is that my G(z) (z is normal distributed noise) is way out of the expected range. Picture - see comparison of real against generated data.(It's also a terrible model, being just a few dense ...

**0**

votes

**1**answer

12 views

### LSTM prediction output for multiple values given a certain time step

I came across a time series prediction problem where I have a dataset with multiple entries. Each entry represents a value of a certain category in a given time. All the entries are indexed by their ...

**0**

votes

**1**answer

15 views

### TensorFlow - predicting next word - loss function logit na target shape

I'm trying to create a language model. I have logit and target of size: [32, 312, 512]Where: .shape[0] is batch_size.shape[1] is sequence_max_len.shape[2] is vocabulary sizeThe question is - ...

**0**

votes

**0**answers

16 views

### Kivy + Tensorflow Interface Hanging

I am beginner to both kivy and Tensorflow.Today, I wrote two codes,one for UI using Kivy which contains some screens and buttons and another code for basic understanding of Multi-Layer Perceptron (...

**1**

vote

**1**answer

16 views

### Keras - Custom Metric producing different values in console vs. model.evaluate()

I am doing a neural network regression problem using Keras with a TensorFlow backend. I need a RMS Error value to determine my model's performance. Unfortunately this does not exist as a out-of-the-...

**1**

vote

**2**answers

14 views

### What is the difference between image mean subtraction and pixel mean subtraction?

I know that we need to center our input data in order to facilitate the NN training with a global scalar learning rate. But what difference does subtracting the pixel mean across all channels (R, G, B)...

**0**

votes

**0**answers

11 views

### Keras get_weights() doesn't show full output

I'm currently using Keras to solve a regression problem. And I want the weights of my layers (embedding layers).I'm using layer.get_weights() from keras, but it doesn't show me the full output....

**0**

votes

**0**answers

14 views

### How to build an image from the class Mat (opencv) obtained from the output of a neural network in java?

At the output of the neural network, I get an object of the class Mat. The object has the following properties:res=Mat [ -1*-1*CV_32FC1, isCont=true, isSubmat=false, nativeObj=0x7f3e56fff160, ...

**0**

votes

**0**answers

43 views

### neural net fails on floating point input

I am trying to implement a simple feed-forward neural net in C++, using Visual Studio. For this test, I've set it up to solve the XOR problem, and the net does fine with discrete inputs. However, If I ...

**0**

votes

**0**answers

12 views

### variables_to_restore has NotFoundError

I have a variable v and want to apply moving average to it. I applied the following steps to save it:import tensorflow as tfv=tf.Variable(0,dtype=tf.float32,name='v')ema=tf.train....

**-1**

votes

**0**answers

26 views

### Configuring Input to Layers Weights in Matlab Neural Network Toolbox

Input one's multiple connections in layer OneThere are 5 neurones in my layer one and I want to 5 weights going there from my every input, lets suppose I just first want to configure it for my first ...

**0**

votes

**0**answers

17 views

### How to give the 1D input to Convolutional Neural Network(CNN) using Keras?

I'm solving a regression problem with Convolutional Neural Network(CNN) using Keras library. I have gone through many examples but failed to understand the concept of input shape to 1D Convolution...