0
votes
0answers
15 views

Tutorial on Radial Basis Function Networks?

I want to learn about Radial Basis Function Neural Networks, can you please suggest a good introduction or tutorial? All the introductions I found are rather short or incomplete or so.
0
votes
1answer
23 views

Decision boundary equation of the perceptron

As I know the standard linear equation has the following form in $R^2$: $w_1 x_1 + w_2 x_2 = b$ where $b$ is the intercept with $x_2$ Also I know that a decision boundary in $R^2$ for a perceptron ...
2
votes
1answer
39 views

Gradient decay in neural networks

I read that in traditional feed-forward neural nets the gradients in the early layers decay very quickly and that this is 'a bad thing'. But I don't understand why. Can someone please explain what ...
6
votes
2answers
557 views

Meaning of a neural network as a black-box?

I often hear people talking about neural networks as something as a black-box that you don't understand what it does or what they mean. I actually I can't understand what they mean by that! If you ...
0
votes
0answers
10 views

Why feature maps are indexed by two indices?

I'm reading about convolutional neural networks. As I understood a feature map is a set of neurons (i.e like a single hidden layer in traditional ANN). So why feature maps are indexed by (i,j)? ...
2
votes
0answers
39 views

Conceptual issues in training neural network and learning curve

I have a 4 Input and 3 Output Neural network trained by particle swarm optimization (PSO) with Mean square error (MSE) as the fitness function using the IRIS Database provided by MATLAB. The fitness ...
0
votes
0answers
15 views

Help about a perceptron question

while studying for my Machine Learning exam, I encountered a problem that I cannot understand. In the problem, we have this perceptron, which 3 binary inputs (0 or 1) a,b,c with respective weights of ...
1
vote
0answers
33 views

Why is the default cost function choice of a neuron quadratic loss?

I'm studying neural networks, and I'm trying to decide why the default choice of cost function for a single neuron seems to be quadratic loss: $$\sum_i(y_i-f_i)^2,$$ instead of: ...
1
vote
1answer
34 views

Why features compression is good?

I'm reading about deep learning and that in principles it's a features compression technique and that is why it works. Now my question is why compressing features from 200 or so into 4 is better? How ...
0
votes
0answers
27 views

What is the best algorithm for finding attacks from log file [on hold]

I m working on forensic analysis of web logs. I have generated the DoS attack dataset and i m having the attack dataset of log files (unlabeled dataset) taken from Dr. Anton Chuvakin. I need to look ...
1
vote
1answer
46 views

Cascade Combination of Kernel Functions

I have a question regarding machine learning and specifically kernel functions. Suppose we have a Kernel function, say $K(x)$, and also another distinct one, say $K'(x)$. I want to know is $K(K'(x))$ ...
0
votes
0answers
16 views

Difficulties in applying activation function in neural network

This is beginner level question. I have several training inputs in binary and for the neural network I am using a sigmoid thresholding function ...
2
votes
1answer
25 views

Can a deep belief network (stacked RBMS) be used solely as a dataset generator?

I have a large dataset (tens of thousands of predictors) on which I would like to perform feature reduction with the intent of better model-building for prediction. Deep Belief Networks seem to ...
0
votes
1answer
22 views

Offline training or batch wise training

Can somebody please explain how to train a neural network in batch mode. I have a single target time series of length $N$ for a given input time series of the same length. In order to apply Hopfield ...
0
votes
1answer
41 views

Issue in training Hopfield network and convergence problem

I am learning how to use Hopfield Neural network as a context addressable memory. The objective is to obtain a fixed point of the network which indicates an equilibrium state. This state vector ...
1
vote
1answer
52 views

What kind of model is used by 20 Questions?

Which kind of machine learning concept / model is used in 20 Questions? Is this kind of thing best solved by a neural network? Where I can read something about it?
0
votes
0answers
35 views

Neural Network, dependence among outputs?

Is there a way to train a neural network in the following manner: You have $n$ observations in the training set. The neural net will start with random weights, and produce $n$ outputs. I want to ...
1
vote
1answer
113 views

How to design neural networks for pattern recognition in biometry?

Having read numerous texts regarding neural networks and their characteristics, I am getting increasingly confused, paradoxically – I am looking for a brief explanation or references to the right ...
0
votes
1answer
17 views

highly sporadic validation error during training with multilayer perceptron

I'm encountering an issue where a classifier I'm developing reports validation errors during training that span a wide range of values without consistently decreasing over time. Unfortunately, I'm new ...
4
votes
1answer
131 views

Bayesian MLPs using the MCMC methods - any tricks of the trade?

Having used the NETLAB library for MATLAB to implement Bayesian Multi-Layer Perceptron (MLP) neural networks using MacKay's evidence framework, I am now experimenting with Markov Chain Monte Carlo ...
1
vote
1answer
36 views

How to initiate bias node in a restricted Boltzman machine

I am new to Neural Networks and trying to implement RBM. I am stuck on initializing the visible layer's bias value. Is it supposed to initialize to some random number or there is some probabilistic ...
0
votes
0answers
34 views

Supervised or unsupervised learning problem?

currently I'm working a pattern recognition problem. I have been using supervised learning (neural network and svm with one class classification) but I think I'm doing it in a wrong way. For ...
0
votes
1answer
24 views

Supervised learning based on phase space representation

Phase space learning Paper1 and Paper2 in neural network represents the input in higher dimension in auto associative learning. So, the network functions as an auto-associative memory where dynamical ...
2
votes
1answer
60 views

Evaluating the clustering of a Kohonen UMatrix

Given a converged Kohonen feature map, how would one evaluate the clustering in terms of intra- and inter-cluster distances? Assuming that both the trained codebook vectors and Unified Distance ...
1
vote
2answers
49 views

Model instability in data mining. When it is big enough to discredit a model and how to measure it?

Let's say I have two models. One has cumulative lift on test data 4.322578, second 2.84488. The only advantage of the second over the first consists in the quality of having the cumulative lift curve ...
1
vote
1answer
51 views

When using a Neural Network to classify more than two classes, is it better to have multiple output nodes (one for each class) or one output node?

Currently, I am using a neural network to classify data into one of three groups (a logistic activation function is used on all but the output nodes). I can train the neural network in two ways: 1) ...
0
votes
1answer
28 views

Layers size in convolution NN

I have a pretty complex function that I'm trying to make my computer learn using CNNs. It involves 70 X 70 grayscaled images. The final output is the output of the last unit (it's because I want to ...
0
votes
1answer
69 views

Supervised learning : Hebb learning rule doubts

(A) In this book "Introduction to Neural Network using Matlab 6.0 - S. N. Sivanandam, S. N Deepa" ...
0
votes
0answers
18 views

Radial basis network character recognition

I want to develop a simple character recognition program by implementing a given neural network kind; a simple command line-type is enough. The radial basis function neural network was assigned to me ...
0
votes
0answers
53 views

Having trouble understanding netflix RBM

According to this paper (pdf), the energy function of the restricted Boltzmann machine (RBM) is defined as: and the paper shows that the conditional probability of softmax unit is: I'm having ...
0
votes
1answer
25 views

Standardising the weights generated from feedforward back propagation NN

I have binary data input to NN. The weights generated by NN are not normalized, i.e., the weights are not the same for every run of the algorithm. How to standardize these weights?
3
votes
0answers
136 views

Is R-squared value appropriate for comparing models?

I'm trying to identify the best model to predict the prices of automobiles, using the prices and features available on automobile classified advertisement sites. For this I used couple a of models ...
0
votes
0answers
14 views

Relationship between momentum and minibatch size, should they be used together?

It seems to me the both momentum and using minibatchs achieves almost the same thing. They both add a form of relating the changes to the weights from other test cases. In minibatch, the weight ...
0
votes
0answers
32 views

Detecting structures in matrices of variable size (link spam)

I'm trying to create an algorithm that would detect link spam structures in directed graphs of nodes (converted to matrices). Each structure is represented by a sparse matrix of links between the ...
0
votes
0answers
39 views

Time Series Ahead Prediction in Neural Network, Large Scale Iterative Training

I am having trouble in implementing neural network to predict N points ahead. My only feature is previous time. I used elman recurrent neural network and also newff. In my scenario I need to predict ...
2
votes
1answer
62 views

Comparison of CPH, accelerated failure time model or neural networks for survival analysis

I am new to survival analysis and I've recently learned that there are different ways to do it given a certain goal. I am interested in actual implementation and appropriateness of these methods. I ...
1
vote
0answers
129 views

Difference between bayesian belief network, fuzzy neural network and fuzzy cognitive map

What is the difference between bayesian belief networks, fuzzy neural networks and fuzzy cognitive maps (FCM)? A fuzzy cognitive map is a combination of fuzzy logic and neural network, used to model ...
3
votes
1answer
79 views

How to make a Neural network understand that multiple inputs are related (to the same entity)?

I am not sure if this is the right place to ask this but here goes: Sometimes times two or more inputs of a neural networks can often be related to a single "real world" entity. E.g : ...
1
vote
3answers
70 views

How to estimate training time prior to training? (Machine Learning & Neural Networks)

I'd like to know ahead of time if my training will take 8 hours, 8 days or 8 weeks. (The 8 was an arbitrary number I chose obviously). Is there a reliable way to estimate the time it will take? Can I ...
0
votes
0answers
74 views

Training Restricted Boltzmann Machines with Bias Units

I have written some code that basically does the following:- 1: creates a matrix of binary features and a matrix of scaled features ( in the range 0 to 1 ) 2: RBM trains separately on each of the ...
0
votes
1answer
40 views

How to set the radius value in self organizing map?

I'm training the self organizig map, I need to set the value for the radius of it. is there any method to find the optimum radius size ?
1
vote
1answer
85 views

Are bias weights essential in the output layer, if one wants a universal function approximator (or non-linearly separable problem solver)?

I am learning about ELM (Extreme Learning Machines) and it appears to have no bias weights at the output layer. Besides that, just to clarify, the kind of ELM I am refering to are topologically no ...
3
votes
1answer
295 views

R neural network model with target vector as output containing survival predictions

Overview I want to simulate the survival prediction using neural networks described in this paper entitled "Application of Artificial Neural Network-Based Survival Analysis on Two Breast Cancer ...
0
votes
0answers
31 views

NN forecasting data source samples

I'm interested about the field of energy consumption forecasting, and because I'm in the learning stage I'm looking for some source codes and samples. More exactly I'm interested about forecasting ...
1
vote
1answer
339 views

Training a convolutional neural network

Based on my research on convolution neural networks, every other layer in such a network has a subsampling operation, in which the resolution of the image is reduced so as to improve generalization of ...
0
votes
0answers
36 views

On the application of an algorithm for classification

Given, a set of training pattern p_1 = [1 -1 -1 -1 -1 1 -1 1 1 1 1 -1 -1 1 1 1 1 -1 -1 1 1 1 1 -1 1 -1 -1 -1 -1 1]'; I can calculate the weight by $W = p_1*p_1'$ ...
1
vote
0answers
35 views

What is exactly code vector and quantization vector of self organizing map?

I am trying to understand code vector in self organizing map. Could anybody explain me intuitively what it is exactly?
1
vote
1answer
181 views

Neural network for prediction

I am working on neural networks for a regression problem in R using packages like nnet, caret etc. I have split my data into ...
2
votes
1answer
76 views

Theoretical performance of different classifiers

I am trying to list the differences in the ways a regularized general linear model would, in theory, be different from a neural network and linear discriminant analysis. I have a case where the ...
0
votes
2answers
135 views

Test data generation for neural network handwriting recognition

Can someone share some Octave/Matlab code or algorithm to pre-process a photo taken from mobile camera of a handwritten digit. After pre-processing, the data should have similar characteristics to ...