Linked Questions

0
votes
1answer
582 views

Is there a rule for number of hidden nodes in a layer and number of hidden layers [duplicate]

Is there a rule of thumb for selecting for a neural network or an autoencoder: (a) Number of hidden neurons (b) Number of hidden layers (c) In general, to begin applying a machine learning ...
11
votes
1answer
45k views

Difference between “in-sample” and “pseudo out-of-sample” forecasts

Is there an explicit difference between in-sample forecasts and pseudo out-of-sample forecasts. Both is meant in the context of evaluating and comparing forecasting models.
12
votes
4answers
5k views

What does “degree of freedom” mean in neural networks?

In Bishop's book "Pattern Classification and Machine Learning", it describes a technique for regularization in the context of neural networks. However, I don't understand a paragraph describing that ...
6
votes
2answers
4k views

Time series prediction: Neural Network (nnetar) vs. exponential smoothing (ets)

When I make a forecast for the univariate time series $x_1=1, x_2=2, \dots, x_{14} = 14$, why does the nnetar() function in R (which uses a neural network) not ...
5
votes
2answers
4k views

ML with fastest classification speed

I have a data classification problem and I'm wondering what is the best machine learning approach to use for the particular constraints of my problem. My constraints are as follows: - the data ...
1
vote
1answer
6k views

Optimum number of epochs and neurons for an LSTM network

I wanted to know if there's a way to select an optimum number of epochs and neurons to forecast a certain time series using LSTM, the motive being automation of the forecasting problem, i.e. the ...
6
votes
1answer
5k views

How to Choose Activation Functions in a Regression Neural Network?

I'm having difficulties with some basics regarding the application of feed forward neural networks for regression. To be specific, lets say that I have an input variable $x \in \mathbb R^4$ and data ...
4
votes
1answer
726 views

Is building deep learning architectures a trial and error scheme?

I have been reading many deep learning papers where each of them follow different architecture. I cannot see what the logical sense or the intuitive sense behind each layer in each architecture. I got ...
2
votes
2answers
2k 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 ...
2
votes
1answer
2k views

Feed forward Neural Network and MSE issues

I've been implementing a Feed-forward Neural Network in C++ and CUDA. It is a basic Multi-layered Feed Forward ANN, using various activation functions (sigmoid bipolar, tanh, tanh scaled, and soft-...
8
votes
0answers
811 views

Universal Approximation Theorem — Neural Networks [closed]

I have posted this question elsewhere--MSE-Meta, MSE, TCS, MetaOptimize. Previously, no one had given a solution. But now, here is a really excellent and comprehensive answer. Universal approximation ...
0
votes
3answers
270 views

Less training data gave me better test score

I'm currently working on a project where I'm also the one who's labelling the data that im going to use for the model. My model is a document-classification model where I'd classify if a document ...
0
votes
1answer
558 views

Size of hidden layer in neural networks for learning specific logical rules

According to this answer, a general rule of thumb is that your hidden layer size should be between your input and output sizes. In developing my JavaScript neural network, this has proven to be about ...
4
votes
1answer
170 views

2 hidden layers are more powerful than 1

When searching for information on choosing the number of hidden layers in a neural network, I have come across the following table mutiple times, including in this answer: | Number of Hidden Layers ...
2
votes
1answer
258 views

Why Neural Network is Failing in a simple classification case

I have the code below where a simple rule based classification data set is formed: ...

15 30 50 per page