Tagged Questions

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
27 views

Choosing the number of principal components to retain before training a neural network for classification

I am working on neural networks and I am currently creating a perceptron that will work as a classifier for a data set of images with faces. I am required to perform pca (principal component analysis) ...
0
votes
1answer
25 views

How to verify that the ANN code is working properly?

First I'm not sure if this is the right place to post my question, but I saw some questions about ANN, and I assumed I can ask it here. I have implemented an ANN with back-propagation. I'm using it ...
0
votes
0answers
22 views

Making a neural network model more sensitive to one of its several inputs

I am currently using neural network methods in R to model energy consumption (response) based on temperatures, previous consumption values and weekend dummy variables (inputs). Unfortunately, the ...
1
vote
0answers
10 views

Multiple Neural Networks with single output neuron vs. Single ANN with multiple output neurons

Main Question Given multiple output parameters that are independent of each other, would multiple ANNs with a single output neuron give better prediction results than a single ANN with multiple ...
0
votes
0answers
17 views

Query on “Deep neural networks for object detection”

I was trying to follow the paper "Deep neural networks for object detection" at http://web.missouri.edu/~hantx/ECE8001/Presentation_papers/Deep%20Neural%20Networks%20for%20Object%20Detection.pdf. I ...
0
votes
0answers
11 views

Using PyBrain after training a network

I'm using PyBrain to create a neural network. I'm still pretty new to neural networks and their concepts. I've so far only run train() over the network, as ...
1
vote
1answer
22 views

How do I incorporate the biases in my feed-forward neural network

I'm trying to implement a FFNN. I'm doing this as an excercise to understand how biases play a role in the classification. I trained a NN using a package in R with the inputs being 1..100 and the ...
0
votes
0answers
7 views

Reinforcement learning for continuous states, discrete actions. Algorithms?

I'm trying to find optimal policy in environment with continuous states (dim. = 20) and discrete actions (3 possible actions). And there is a specific moment: for optimal policy one action (call it ...
0
votes
0answers
13 views

Predicting the near-future values using an unevenly sampled time-series data

Summary Need help with predicting the near-future values using an unevenly sampled time-series data. Data is collected as events, and is converted to time series. I have tried out a few approached ...
0
votes
0answers
15 views

Feedforward Neural Net, can I make hidden neurons to learn independent features?

For example I'm writing a 1-hidden layer net to evaluate chess positions. The inputs are 800+ binary neurons, first 768 are 64 squares x 12 pieces. The next 20 are piece counts, 10 pieces (don't need ...
0
votes
0answers
4 views

Trying to use neural network to minimize my error function

I wish to minimize my error function which I have in the form of $e(t+1)= f(e(t)) + g(e(t))u$. The error is $e$, $f$ and $g$ are functions of error while $u$ is the control. My aim is to obtain an ...
0
votes
0answers
10 views

“sensorial/physical” information -> neural network -> textual/vocal/physical response [closed]

How could we train a hypothetical neural network that outputs "real-time" textual/vocal/physical "action" responses to inputs of sensorial(visual/auditive/olfactive/.../physical) "information" ?
0
votes
0answers
9 views

Is backpropagation algorithm same for both full-connected and local-connected neural network?

is backpropagation algorithm same for both full-connected and local-connected neural network? I know how to use the BP for a full-connected network, but I don't know how to use the BP for a local ...
1
vote
1answer
30 views

Unclear area in Convolutional Neural Net

I have a question about the conv neural net. Specially from the deeplearning tutorial at http://deeplearning.net/tutorial/lenet.html. In Fig 1 from that url, (and also similarly in between C3 and ...
0
votes
0answers
20 views

Weights Initialization of Neural Network

I recently checked several initialization strategies of neural network from my friends' implementation. First one is classic one which initializes weights randomly from gaussian distribution with a ...
1
vote
0answers
11 views

How features are representation in deep learning

I'm trying to build a deep neural network for mobile phone data. I've been doing different tutorials, but there are some basics concerning how the hidden units represents features that I really would ...
0
votes
0answers
28 views

Why does my output from an RBM look so noisy? [closed]

I am designing Gaussian Bernoulli restricted Boltzman machine. To train this model, I followed the CD-1 algorithm. To evaluate its performance, I visualized the input and the reconstructed input of ...
0
votes
1answer
26 views

Is it the correct usage of nnet in R

I have a dataset that looks like this : ...
1
vote
2answers
32 views

Neural Network General Learning Dynamics of Gradient Descent

This might be simple to you but can someone tell me step by step how is matrix form of updating rule of $W^{32}$ and $W^{21}$ derived in this case? Consider linear three layer neural network model ...
1
vote
1answer
45 views

Problem on time-series

I am dealing with event data (recorded over a month) which gives out a binary response from a sensor when a door opens or closes - the time is noted at every instant and can also be represented in ...
0
votes
0answers
27 views

One or two output neurons for a binary classification task with an artificial neural network

Suppose you have a classification problem in which you want to classify inputs into two exclusive classes (y1 and y2) with an artificial neural network (which models P(y|x)). Among the two following ...
0
votes
0answers
22 views

R PNN slow- other packages?

I'm trying to run a pnn (Probabilistic neural network) in R, using pnn package. It's function smooth uses rgenoud package to optimize. I only used 9k lines and it's real slow. Is there any other ...
1
vote
2answers
44 views

Strategies for parallelising neural networks

When it comes to parallelising a problem, it involves the division of routines and subroutines between a number of nodes, namely; the master node and the slave nodes. Once each of these nodes ...
1
vote
1answer
53 views

Predicting continuous output

I'm trying to predict output per worker for given inputs of capital (physical capital), labor (human capital) & productivity. I have a data set of several countries ...
0
votes
0answers
9 views

Training set wireless forensics tool

I'm working on a wireless forensics tool, starting with simple Dos attack ( de-authentication, disassociation, etc... ) before I start the very exhausting task of making my own training set, I thought ...
0
votes
1answer
32 views

How we can add new data in training time of neural network without stopping it in MATLAB?

I have a binary classification problem. Now I'm using patternnet in MATLAB R2014b to design a neural network for this problem. ...
0
votes
0answers
22 views

Training Neural Network with Highly Correlated Inputs

I am trying to train a basic Neural Network to predict Football final scores based on: i) Time in the match ii) Current Score iii) Parameters representing strength of home and away team. In order ...
0
votes
0answers
17 views

using SAS for decision tree

I am quite new to SAS. I wanted to figure out how we can use Test dataset and Train dataset seperately. As of now i was dividing the existing dataset into Training and Test dataset. My requirement is ...
0
votes
0answers
16 views

Controllability in Neural Networks

I'm going to start my master thesis in about 2 months. I've had a course on general AI approaches. (Reinforcement learning (MCTS), neuroevolution, Neural Network (perceptron and backpropagation etc). ...
0
votes
0answers
15 views

How do I implement custom sparse connections in a neural network?

We'd like to implement neural network which is not fully connected - we want to explicitly set which output neurons connect to which input neurons (there's no hidden layer). We use Theano but we can ...
0
votes
0answers
11 views

r-pnn, normalization and different distance measures for each variable

Since pnn is a NN that uses a Radial kernel to classify data, I think the distance measure is key and, in consequence, the normalization of the data. Am I right? How does pnn package calculate the ...
0
votes
0answers
41 views

What are the advantages of deep convolutional neural network over shallow one?

I know that deep convolutional neural network(cnn) helps reducing the number of free parameters in training. What are other advantages of using deep cnn over shallow cnn?
1
vote
2answers
43 views

Can we learn 3d features using Autoencoder?

Typically, we use Autoencoder to learn 2d features on 2d images (e.g. pen-strokes of digit). For example, if I have 10000 3d 31x31x31 images (e.g. car images). I unroll each of the images, i.e. ...
0
votes
0answers
19 views

Naive Bayes Produce Confidence

I am pretty newbie in machine learning. Please forgive and point out anyone incorrect use of terminology. Now I am learning Naive Bayes algorithm. As I have learned Neural Network, when predicting, ...
1
vote
0answers
21 views

why pretraining for convolutional neural networks

Usually Back propagation NN has the problem of vanishing gradients. I found that Convolutional NN (CNN) some how get rid of this vanishing gradient problems (why?). Also in some papers some ...
0
votes
0answers
26 views

What does “shift invariant” mean in convolutional neural network?

I saw a term describing the feature detectors, i.e. shift invariant. What is that mean? Paper: 1989 Generalization and Network Design Strategies
0
votes
0answers
12 views

Neural Network JavaScript Form Field Validation

I want to build a neural network and ultimately end up with functions that can validate various types of data in a web form using JavaScript. This way I can create new data types by telling the ...
0
votes
1answer
42 views

“Vanilla” neural network model (Hastie et al.)

Hastie et al. (The elements of statistical learning) discuss "vanilla" neural network model on page 392. They describe the model as: Derived features $Z_m$ are created from linear combinations of ...
1
vote
1answer
38 views

Multi Output Neural Networks

Up until know I only used neural networks to classify a single output, I set one output neuron for each class and check which neuron has the highest/lowest activation. What I am trying to do is to ...
0
votes
0answers
18 views

Early stopping methods for ANN applied to series prediction

Could anyone give advice or links to advice on early stopping methods for ANN trained with back prop applied to time series prediction? I know some methods for classification tasks but don't the ...
0
votes
0answers
29 views

Neural Network for hand written digit recognition

I have create the neural network with three layers. 1 layer - 500 inputs 2 layer - 500 inputs 3 layer - 10 output classes. I have synthesized the ...
0
votes
1answer
30 views

Convolutional neural network with non-image input data

Can CNNs be used with input data which is not an image? The reason I'm asking is because the original image is often clipped in size because of border effects when doing the convolution. But if the ...
1
vote
0answers
21 views

How do we get/define filters in convolutional neural networks?

How do i obtain filters from convulutional neural network(CNN)? My idea is something like this: Do random images of the input images (28x28) and get random patches (8x8). Then use autoencoders to ...
1
vote
1answer
38 views

Does Deep network (e.g. # of hidden layer=2) always better than shallow network (i.e. # of hidden layer=1)?

I attempted to build a deep network (e.g. deep autoencoder) for some object classification, my result showed that the deep networks is worst than shallow network. However, from what I have read from ...
0
votes
1answer
16 views

What does training correlation coefficient means in ANN prediction

I'm a beginner in statistics with limited knowledge. I'm reading up on neural networks to predict outputs using inputs. I understand that a neural network has to be trained to produce the Least mean ...
0
votes
0answers
18 views

Graphically, how does the non-linear activation function project the input onto the classification space?

I am finding a very hard time to visualize how the activation function actually manages to classify non-linearly separable training data sets. Why does the activation function (e.g tanh function) ...
0
votes
0answers
12 views

What guidelines should be followed for using Neural Networks with sparse inputs

I have extremely sparse inputs, e.g. locations of certain features in an input image. Further each feature can have multiple detections (not sure if this will have a bearing on the design of the ...
1
vote
1answer
29 views

How to apply the output layer function in a neural network

I am implementing a Neural Network in a somewhat different fashion. I train my neural network locally using a small subset, and export the weights. My goal is to test the neural network in a ...
0
votes
1answer
22 views

Different activation function in nnet R

Can different activation functions be specified for hidden and output layers for any of the R neural network packages?
1
vote
2answers
36 views

What does “permutation invariant” mean?

I have seen a term "permutation invariant" version of the MNIST digit recognition task. What does it mean?