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

0
votes
0answers
12 views

The ethics of using an optimal multiclass feature set for binary classification

I'm currently trying to find the best feature set/network architecture configuration for a binary classification problem, however to approach it via the usual means of building and testing does not ...
0
votes
0answers
15 views

Finding best neural network structure using optimization algorithms and cross-validation

I'm using optimization algorithm to find best structure+inputs of a patternnet neural network in MATLAB R2014a using ...
0
votes
3answers
48 views

How to Use Neural Networks to Forecast Time Series Data with Predictor Variables?

I have browsed a lot of topics here, but the ones I see were all about forecasting a single variable, depending on its historical values. Whereas I want to predict a variable, by estimating a ...
0
votes
1answer
20 views

Composition of bankruptcy probability and firm size

I'm using neural network for a binary classification problem of bankruptcy prediction using patternnet function in MATLAB, so i ...
0
votes
0answers
11 views

How to derive the gradient formula for the Maximum Likelihood in RBM?

I am learning RBM (restricted Boltzmann machine) for deep learning. The log-likelihood of RBM is given as : and its gradient w.r.t. the parameter is: I don't understand how is the gradient ...
1
vote
1answer
37 views

What's the relation between deep learning and extreme learning machine?

Often I have found deep learning and extreme learning machine discussed together. Based on my little knowledge of the subject my impression is that they are different methods with different aims. ...
0
votes
2answers
39 views

Test data results does not match with cross validation results

I'm confused with my data I'm currently playing with. I have a data set which holds 58 attributes in 10000 instances. Attributes are 56 float values typically within 0 to 1. Then there is nominal ...
0
votes
0answers
10 views

NN: Should we apply weight decay to the bias?

In CS294A lecture notes, Andrew Ng writes (about autoencoders): "Usually weight decay is not applied to the bias terms... Applying weight decay to the bias units usually makes only a small different ...
1
vote
2answers
12 views

Epoch vs Incremental Update over Entire Dataset

In the context of neural networks, what is the difference between training like this: ...
0
votes
0answers
12 views

Multilayer perceptron 3 classes

I need to create a MLP for 3 classes. I don't know to to do the structure. I thought that having one hidden layer (don't know how many nodes) and and output layer with 2 nodes would be enough, like ...
0
votes
0answers
24 views

Adaboost for neural networks. Is it still worth it?

I have a question about Adaboost and neural networks. Given the recent development in neural networks (dropout, maxout, or rectified linear units) is there a significant benefit of performing Adaboost ...
0
votes
0answers
33 views

how to calculate Root Mean Square Error (RMSE) for predicted Probability Density Function (PDF) in Matlab

I have used Mixture Density Networks for probability density function prediction. I am wondering how I can calculate Root Mean Square Error (RMSE) of predicted pdf in MATLAB. Thanks.
3
votes
2answers
69 views

Linear post-treatment of nonlinear regression

I have often found in practice, using nonlinear regression techniques such as feedforward neural nets or random forests, that the resulting actual-vs-fitted plot (on training set) seems obviously ...
0
votes
0answers
8 views

Function domain as a problem for linear output unit

I'm doing some regression using neural net(using MLP implementation from http://deeplearning.net/tutorial/mlp.html, I used my own but it produced the same results before I opted for this one), ...
0
votes
2answers
178 views

Does feature standardization always make sense?

I wonder if feature scaling like this makes always sense for neural networks: Let $T$ be the training set and $x_i \in \mathbb{R}^n$ with $d_i \in T$ be the feature vector of $d_i$. Then add another ...
1
vote
2answers
36 views

Does the activation function of output layer differ during training and already trained network?

I'm creating and OCR app, and so far it seams to work. It's quite similar to example from Coursera - Machine learning course. Output layer of network has as many neurons as classes needed to ...
1
vote
0answers
13 views

Applying autoencoders for dimensionality reduction in audio: Why does this create a low-pass effect? [closed]

I've been playing around with framing audio data and training a single-layer autoencoder to find a dimensionality-reduced form (say 128-sample frames to 32-dimension frames). When I test the audio ...
0
votes
1answer
41 views

Convert continues number to integer number in optimization algorithms in MATLAB

I'm using a continuous optimization algorithm for optimizing neural network's number of neurons in first and second layers besides feature selection so I used this structure for converting continues ...
1
vote
0answers
13 views

Is NN saturation always bad?

I am trying to analyse the effect of hidden unit saturation (outputting mostly 0 and 1 for sigmoid, and not much in-between) on the neural network training performance, and I feel a bit stuck, ...
1
vote
0answers
28 views

Pre-training deep neural networks by supervised learning

When pre-training deep neural networks layer by layer, is it normal to pre-train the layers -which haven't been pre-trained by unsupervised training- by using supervised training before we train the ...
0
votes
0answers
19 views

auto-steering using neural networks

I was hoping if anyone could point me in right direction, I want to implement a neural network that could steer an autonomous car, I have implemented basic classification problems before using single ...
0
votes
1answer
18 views

Reported error rates on neural networks

It is common to depict the error rates of types of neural networks in a table, for example, see the MNIST website. However, because of the non-determinism caused by weight initialization the actual ...
0
votes
0answers
26 views

How calculate average probabilities in MLP or SVM?

I have a system that find best model (best inputs and parameters of MLP/SVM) model in a financial problem for every inserted database and create a specific model for a specific data sample. I'm using ...
1
vote
0answers
30 views

Neural Networks and Picture Recognition

I have spent a bunch of time looking at this series of videos (Neural Network Tutorial), by Ryan Harris: https://www.youtube.com/watch?v=Q_5B3GuWPCc&index=41&list=PL29C61214F2146796 I am ...
0
votes
1answer
57 views

Feeding a layer from a deep-learnt neural network into an SVM

In http://jmlr.org/proceedings/papers/v32/donahue14.pdf, it is stated: Our top-performing method (based on validation accuracy) trains a linear SVM on DeCAF6 Can you delineate in a way ...
0
votes
0answers
11 views

How do current image-to-3D model systems work?

I understand that at least one system for automatically modeling 3D objects from image data exists. Autodesk appears to have developed a good method. Does anyone know the basic structure and ...
1
vote
0answers
19 views

How to give an input when you are using Machine Learning method in R

I am new to R and machine learning algorithms. I have basic knowledge of different machine learning algorithms. I have four years of daily sales data.I am trying to predict sales using Support Vector ...
-1
votes
0answers
22 views

How to compare a Cox model with a neural network model [duplicate]

I am trying to compare a Cox model with ANN in R, but I have some problems: The result of package coxph is a hazard rate, but the result of package ...
2
votes
2answers
33 views

Regression vs Multiclassification

I was working with SVR, and wondering, why can't I solve a natural regression problem as a multiclassification task ? Example: I have for a regression problem: targets 1, 5 and 10, trying to fit ...
0
votes
1answer
18 views

output of a non linear neuron

If a neuron uses a non linear activation function such as a sigmoid function, then the output of that neuron can be any value between 0 and 1. suppose if the activation function results in value like ...
0
votes
1answer
18 views

Difference between a non-linear neuron vs non-linear activation function

I need to know the difference between a non-linear neuron vs non-linear activation function AND linear neuron vs linear activation function.
0
votes
0answers
20 views

Custom Neural network in matlab

I am trying to make a custom Neural network structure using 'network' command. I am a little confused.Can we change the connections between individual neurons?Like it is possible in weka?
0
votes
0answers
39 views

MATLAB interperetation of Neural networks

I am new to Neural networks and I am trying to build a custom neural network using the NN toolbox in MATLAB.I am using the "create custom neural network function". Now, I find the neural network ...
0
votes
0answers
10 views

results for neural network model - r or r2?

I am wondering what is the best way to report the model performance for artifical neural networks (regression). At the moment, I have a table with r value and the sum of squares error for the ...
0
votes
0answers
22 views

Rprop implementation in C# [migrated]

I'm trying to implement rprop by using my old backprop code as a basis. I'm working on a perceptron with one hidden layer. Rprop algorithm is fairly simple, but I haven't figured all things out. This ...
0
votes
0answers
36 views

Neural-Net style pattern recognition with an unknown/varying number of inputs?

Say for example I had a weighted graph such that each node had an associated value. The nodes' values are given by some function of the edge weights and the number of edges as well as the node's ...
2
votes
1answer
55 views

Can neural net extrapolate output value

Let's assume we have a training set with $y \in \mathbb{R}$. Thus all the data is between $y_{min}$ and $y_{max}$. If we built a decision tree model it cannot return $y_{pred}$ outside the given range ...
0
votes
1answer
54 views

In convolutional neural networks, how to prevent the overfitting?

Given certain amount of labeled data, we define the net structure, such as number of layers, types of layers, the number of convolutional layers, the number of pooling layers, etc. And train the ...
0
votes
1answer
25 views

What is linear separability of classes and how to determine

This question may seem too trivial but my basics are not strong and I shall appreciate help in these concepts. For an n dimensional feature vector and 3 class problem does linear separability need to ...
0
votes
0answers
22 views

Neural network and dynamical system

Dynamical systemsare those whose evolution can be described by a rule, evolves with time and is deterministic. In this context can I say that Neural networks have a rule of evolution which is the ...
0
votes
1answer
30 views

What is R squared for a neural network and what does it signify?

I calculated R square for my neural network based on a formula I found somewhere, which goes something like: http://i.stack.imgur.com/DojZC.png It should be something around 0.98-0.99. But, when I ...
0
votes
0answers
40 views

Algorithm for online handwriting recognition

Is there any specific algorithm for online handwriting recognition? The algorithm should recognize non-cursive and cursive handwriting. I know there is already a similar post on stackoverflow.com, ...
0
votes
2answers
24 views

How is the “classification error rate” of an artificial neural network calculated?

Frequently I see artificial neural networks compared by their "classification error rates" or "error rates", particularly for multi-class problems like CIFAR-10. What does this error rate actually ...
0
votes
0answers
34 views

How to understand this objective function in deep learning

I'm going through Christopher Manning's tutorial from NAACL 2013 "Deep Learning for NLP (without Magic)" and he gets to the point where he's showing how to do unsupervised pre-training. He's saying ...
1
vote
1answer
76 views

Does the vanishing gradient in RNNs present a problem?

One of the often cited issues in RNN training is the vanishing gradient problem [1,2,3,4]. However, I came across several papers by Anton Maximilian Schaefer, Steffen Udluft and Hans-Georg Zimmermann ...
2
votes
2answers
86 views

Which classifiers work well with unbalanced data?

I have a binary classification problem which is very unbalanced - it can have 98% of data from one class. Which classifiers work well with this sort of data? I have an unlimited supply of training ...
0
votes
0answers
79 views

10 fold cross validation model in weka

Trying to build a specific Neural Network arcitecture and testing it using 10 fold cross validation of a dataset. Now building the model is a tedious job and Weka expects me to make it 10 times for ...
0
votes
2answers
30 views

Good machine learning models for confusable categories

I'm using the word confusable to represent similar looking glyphs in text. I'm building an optical character recognition tool with the primary goal of experimenting with machine learning – especially ...
0
votes
0answers
45 views

Arima model - multi step forecast

The following code shows a forecast of the next 24 hours of my electricity prices with two exogenous variables. My problem is, that I don't know how to build a forecast for the next 3 days or more ...
0
votes
0answers
18 views

Forensics in wireless networks, anomaly detection and beyond?

first i'de like to apologize if this is not the right place. Next year i'm gonna be working on my final project in computer security, i have to build a wireless forensics tool that can analyse a data ...