Satyanarayana Vusirikala

9 Questions 11 Answers 0 Followers

Questions related from Satyanarayana Vusirikala

How to apply the k-cross validation technique when the data is in the form time series?

I am dealing with Climate data mining using neural networks. Using rainfall data of 1900 - 1970 year, I have to predict rainfall for 1971 year. In this case, how to apply k-cross validation...

08 August 2014 6,311 11 View

What is the difference between data mining, pattern recognition, machine learning and artificial intelligence?

I am working in artificial neural networks from 5 months. But, up to now I couldn't figure out any difference between data mining, machine learning and artificial intelligence. Can anyone please...

08 August 2014 7,302 5 View

What is the difference between dropout method and adding noise in case of autoencoder?

Motivated by "Improving Neural Networks with Dropout" thesis, In page 2 of the paper, author says that "Dropout can also be interpreted as a way of regularizing a neural network by adding noise to...

08 August 2014 449 3 View

Can anyone please suggest good resources for learning information retrieval

I have been working in artificial neural networks since 6 months. Now, I want to learn about information retrieval. As I don't have any knowledge in it, can anyone please point out some good...

08 August 2014 4,079 1 View

Why is the conjugate gradient method not suitable with dropout? Is the conjugate gradient method suitable for denoising autoencoder?

I was implementing dropout method with conjugate gradient method of updating weights. As I was not getting good results, Hinton sir said that "conjugate gradient is no good with a stochastic...

07 July 2014 7,160 1 View

How can I measure variance of a model?

Is there a good way to measure variance of model experimentally? I mean, can we give a single real number stating variance of the model? Truly speaking, I want to measure the level of overfitting...

06 June 2014 4,078 4 View

What can I do if a validation error continuously increases?

I am coding a neural network. I am following k fold cross validation technique to avoid overfitting. So, I divided dataset into 10 parts and ran 10 fold cross validation. But, I found that cross...

06 June 2014 9,875 7 View

How to solve overfitting problems when the training set is small?

I am currently coding a neural network on weather data. So, I have only 570 training examples. But, the relation between output and input is highly non linear. How can I reduce overfitting on this...

06 June 2014 1,159 6 View

How to perform a stepwise feature selection method in neural networks?

I heard of stepwise feature selection methods for regression problems. How can we perform stepwise feature selection methods when dealing with neural networks? Isn't it computationally expensive?...

06 June 2014 7,334 9 View