Neural networks traditionally refer to a network or circuit of biological neurons. The modern usage of the term often refers to artificial neural networks (ANN), which are composed of artificial neurons or nodes - programming constructs that mimic the properties of biological neurons. ANN are ...

learn more… | top users | synonyms

1
vote
2answers
18 views

Feature selection before neural network classification

I have a training set of 87 samples and 9480 variables. My predictors are continuous and my response variable is binary. I'd like to use the caret package in R to tune a neural network classification ...
0
votes
0answers
11 views

Sensitivity analysis of machine learning techniques

As you know we can have sensitivity analysis (sensitivity of output(s) based on changing of inputs) in different kinds of regression. Can we have sensitivity analysis for machine learning techniques ...
0
votes
0answers
8 views

How to select topology for neural network?

I was given a target function to design neural network and train: (y = (x1 ∧ x2) ∨ (x3 ∧ x4)) The number of input and number of output seems obvious (4 and 1). And the training data can use truth ...
5
votes
2answers
181 views

Timeseries analysis procedure and methods using R

I am working on a small project where we are trying to predict the prices of commodities (Oil, Aluminium, Tin, etc.) for the next 6 months. I have 12 such variables to predict and I have data from ...
0
votes
0answers
6 views

Can the rectangular function be used to filter out magnitudes in logistic regression to add more flexibility?

I would like to use logistic regression rather than an artificial neural network to be able to more easily interpret the results. I would like though to be able remove the linearity by introducing a ...
0
votes
1answer
29 views

Classification when some classes are dependent

I think my problem can easier be explained via an example: Assume we have a dataset containing the images of 10 different mammals, let's say lion, elephant, cat, ... and horse. We have a 20-class ...
1
vote
2answers
112 views

How can an artificial neural network ANN, be used for unsupervised clustering?

I understand how an artificial neural network (ANN), can be trained in a supervised manner using backpropogation to improve the fitting by decreasing the error in ...
0
votes
0answers
16 views

Neuralnet function error in R [on hold]

I try to run neuralnet() in R, which have response variable as diabetes (categorical) as function of 8 predictors (with one ...
0
votes
2answers
12 views

Neural networks: Active input range of activation functions?

I'm playing with the Neural Network toolbox in MATLAB. I've noted that each activation function (aka, transfer function) has 2 properties: the output range, which, if I understand, is the codomain ...
0
votes
0answers
28 views

How to set up neural network to output ordinal data?

I have a neural network set up to predict something where the output variable is ordinal. I will describe below using three possible outputs A < B < C. It is pretty obvious how to use a ...
1
vote
1answer
15 views

How to find $\arg\max$ of a neural network?

Let's say I have a neural network $f$ that takes input $\vec x \in \mathbb {R}^n$ and produces output $f(\vec x) \in \mathbb{R}$. How can I find $\hat x = \underset{\vec x}{\arg\max} \; f(\vec x)$?
0
votes
0answers
9 views

Software packages for neural network [migrated]

I am looking for a very lightweight neural network package to solve the following problem: 2 input units, 4 hidden units, 2 output units different activation functions for different connections ...
0
votes
0answers
13 views

Which classifier to be used in a recommendation problem?

I am supposed to deal with a recommendation problem in which the input vectors of 1 million bits represents the interest of 1 million people in a special product and the output would be the a binary ...
3
votes
1answer
25 views

Temporal convolution for NLP [on hold]

I'm trying to follow Kalchbrenner et al. 2014 (http://nal.co/papers/Kalchbrenner_DCNN_ACL14) (and basically most of the papers in the last 2 years which applied CNNs to NLP tasks) and implement the ...
1
vote
1answer
46 views

Quantitative importance for interacting variables in Artificial Neural Networks?

Is there any common/sound method to quantify (similar to T-test or F-test in regression models) the measures of influence and significance of terms in Artificial Neural Networks? By terms I mean both ...
-1
votes
0answers
33 views

Optimal brain damage in R [on hold]

Is there any R package implementing optimal brain damage algorithm or anything similar what can be used to prune neural networks models?
0
votes
1answer
23 views

Can we boosting or stacking with different input variables for each model in machine learning?

I have a question about Boosting and stacking in machine learning. Suppose that I will train neural network, SVM and logistic regression using optimization algorithm to optimize best inputs in first ...
1
vote
0answers
20 views

Cross-validation for parameter tuning in data mining process (KDD)

In my project I want to compare different classification algorithms to solve a specific problem with a specific dataset. To do this, I divided the dataset in 2 parts. With the first (bigger) part I ...
0
votes
1answer
62 views

How to transform categorical variable into numerical variable when using SVM or Neural Network

To use SVM or Neural Network it needs to transform categorical variables into numeric variables, the normal method in this case is to use 0-1 binary values with the k-th categorical value transformed ...
0
votes
1answer
24 views

SOM dimension doubt

I'm currently working on a research of data clustering using an ANN for self-organizing maps. I'm performing experiments using Matlab, over a Dataset of 20,000 samples and almost 80 variables. The ...
0
votes
0answers
13 views

How to represent website as a fixed size vector?

Generally speaking, how to transform a hierarchical tree structure into a fixed size vector? I have a set (tens of thousands) of websites as my input data. Each website is represented by HTML ...
2
votes
1answer
23 views

How to handle changing input vector length with neural networks

I want to train a neural network with a sequence of character as an input vector. Learning examples have different length and for this reason I don't know how to represent them. Let's say I have two ...
0
votes
1answer
75 views

How to pass the sequential var. length data for the NN?

The main task is from Inductive Logic Programming (ILP) area. The task related to ANN is inspired by paper below but is applied to more complex case.Learning an approximation to clause evaluation ...
0
votes
1answer
26 views

Partitioning for 10-fold cross validation using neural networks in MATLAB

I am working on an assignment which is set to recognize on of 6 basic human emotions based on facial expression data. The data set looks like this: input data: Nx136, where N is the total number of ...
0
votes
0answers
13 views

Activation functions for z-score data

I'm currently using a neural network to try modeling z-score data. Because of the 68, 95, 99.7 rule, I naturally want to have an activation function that has the characteristics that Starts to ...
0
votes
1answer
88 views

From the Perceptron rule to Gradient Descent: How are Perceptrons with a sigmoid activation function different from Logistic Regression?

Essentially, my question is that in multilayer Perceptrons, perceptrons are used with a sigmoid activation function. So that in the update rule $\hat{y}$ is calculated as $$\hat{y} = ...
0
votes
1answer
39 views

neural network high misclassification rate

I have to create a binary classifier for a dataset of approx 150 samples and 50 binary features. The classifier has to be a feedforward neural network (NN). My problem is that while the NN performs ...
0
votes
0answers
19 views

Negative samples on multiclass neural network training

I want to train a deep neural network to classify images. In every implementation I have seen, multiclass training uses only the positive examples for each class. Is there any way to utilize ...
0
votes
0answers
29 views

If my classifier is trained on PCA compressed images, do I have to use PCA compressed images during live?

Recently I discovered how to use PCA to compress my images (for dimensionality reduction). These images are then used to train an ANN image classifier. The purpose of the classifier is to classify ...
0
votes
2answers
23 views

Classification of corpus into classes with imbalanced datasets

i am trying to classify some images in classes using the convolutional networks approach. However there are varying numbers of training examples per class. I am worried that that might cause ...
2
votes
0answers
15 views

Are ANN robust to change in magnitude in the data?

One thing I don't understand about classifier is that whether or not they are robust against variation in magnitude in the training set. For example, for a signal classifier application, I feed into ...
0
votes
1answer
55 views

Neural Network - Classification from Time series

I'm a .Net programmer who is fairly new to neural networks, but I know some of the concepts. I have connected .Net to my copy of Mathematica 10 This is a classification Our business problem is ...
0
votes
0answers
87 views

What is the architecture of a Stacked Convolutional Autoencoder

So I am trying to do pre training on images of humans using convolutional nets. I read the papers http://people.idsia.ch/~ciresan/data/icann2011.pdf and ...
0
votes
1answer
15 views

Do word embeddings impact neural network performance?

Ok, this sounds like a stupid question, but I'm confused about something. Consider a simple neural network with word embeddings as inputs. Suppose $x$ is a one-hot binary vector representing a word. ...
0
votes
0answers
16 views

Neural Network - Real world example

Is there a good example for understanding how to develop a neural network for a particular problem. After studying some mathematical stuff and viewing some videos I got some intuition how this works. ...
0
votes
0answers
22 views

Hessian-Free instead of LSTM for Recurrent Net Machine Translation

Last year, Ilya Sutskever and collaborators came out with a paper about a recurrent LSTM net that learns sequence to sequence mappings for machine translation. It's somewhat surprising that the ...
1
vote
1answer
33 views

Does the recurrent neural network require the length of input samples all the same

Theoretically, the training of RNN doesn't require that the samples must have the same time length, but it seems to me that some software or open-source requires that the input data has the same time ...
1
vote
2answers
28 views

Should I use epochs > 1 when training data is unlimited?

If I have virtually endless training data (it's synthesized) is there still purpose in having epochs? I.e. training on the same samples multiple times?
0
votes
1answer
59 views

Using randomized search algorithms to find weights for neural network?

I am currently taking a class in machine learning. I had mentioned to a coworker that we were learning about randomized optimization, specifically randomized hill climbing (RHC). He said that it was ...
0
votes
1answer
34 views

Concept of Hopfield Networks

Just want to double check my understanding of comcept of Hopfield networks. would a trained hopfield network have an energy function that has local minimas equal to the number of the training ...
0
votes
1answer
34 views

How to calculate the total error of a neural network

I know that my question sounds really simple, but honestly I don't know how to calculate it. The error = expected output- estimated output, but what does total error mean? Is it the sum of the error ...
-1
votes
2answers
40 views

What is meant by the term “convergence” in Restricted Boltzmann Machine?

I have come across the term "convergence" in training RBM. Can someone give a brief definition / explanation of it?
0
votes
0answers
26 views

Regulation term disappears during taking gradient of cost function by using backpropagation

I'm trying to take derivative of cost function with respect to parameter $\theta$. The problem is $\frac{dJ(\theta)}{d\theta}$, somehow, is not equal to $\frac{dJ(\theta)}{dz}\cdot ...
0
votes
0answers
53 views

Estimating the parameters in Neural Network

In the setting of Neural Network (NN). We have a data set, $(Y,\boldsymbol{X})$, where $Y\in\mathbb{R}^n$ is the response variable and $\boldsymbol{X}\in\mathbb{R}^{n\times p}$. We want to fit the ...
1
vote
1answer
42 views

Do Neural Networks need “compound” features?

Apologies if I haven't got the terminology quite right. I have a question about Neural Networks, and I'm not sure exactly the best way to ask it! Hypothetically, let's say I have a dataset of houses ...
0
votes
1answer
46 views

Neural Nets, Lasso regularization

How does one implement lasso regularization or elastic net on neural networks? (feed forward in particular). I know that closed form solutions for this problems don't exist, still how are they ...
0
votes
1answer
57 views

Perceptrons and Decision Boundaries

I am currently studying neural networks and have been trying to reason about this for a while to no avail. I understand that given a perceptron(such as above) with f as a step function, any ...
1
vote
0answers
207 views

Reinforcement learning with Neural Fitted Q-iteration

I have recently read this article - Neural Fitted Q Iteration - Machine Learning and I have tried implement in Python with PyBrain and NumPy on a simple task. The task is a point representation in ...
2
votes
1answer
47 views

How to measure co-adaptation occuring in a multi-layer perceptron neural network that does not use a drop out?

The dropout proposed by Hinton is said to prevent co-adaptation. My question is how can I measure the co-adaptation that occurs in a multi-layer perceptron that does not use a drop out?
1
vote
1answer
55 views

Is there any neural network whose output can be probabilistic, just like multi-class logistic regression?

I want to add nonlinear character into multi-class logistic regression. I know kernel logistic regression can do it. Is there any kind of neural network which has similar characteristic?