Is Sparse autoencoder still very helpful, or it is being replaced by some other techniques in deep learning?

03 March 2017 1 2K Report

These days I am not seeing any posts related with Sparse AutoEncoder (SAE). I read one post of Andrew Ng, 2015 about it. I am curious if it still useful or there are some other better methods in deep learning for this. I am trying to use SAE for one problem.

Thank you.

Ahmed Ben Said

In my opinion everything is useful, it depends on your data. In some cases adding dropout gives better performance, in some cases not. Going deeper is usually better. L1/L2 regularization may work.

Badges
Science topic

More Shyam Krishna Khadka's questions See All

In an unsupervised machine learning alogrithm like autoencoder, is it always necessary to split dataset into train, test and validation set ?

Generally in supervised machine learning algorithms, the model performance is measured splitting train, test, validation set. But in case of unsupervised method , like autoencoder, is it...

01 February 2018 1,477 0 View

What are the best sources for wireless sensor network datasets, to be used for experimental purpose ?

I want to do some experiments with wireless sensor network. I am looking for datasets like UCL ML, or other web resources to download such datasets. Ideally, I would like to have a dataset that...

05 June 2017 6,597 4 View

Can a neural network model have higher accuracy in test set although it has the highest validation loss value than others ?

I am training 3 different models, with varying parameters like learning_rate, regularization_strength. But number of epochs is same for all. For a fixed no. of epoch, model 2 has the highest...

02 March 2017 9,374 2 View

Should the output function for outer layer and activation function of hidden layer in auto encoder be same ?

I have created my synthetic datasets from mixture of Gaussians with k number of components, and 2 dimensions. The data are in the range of 1-100. Now I feed it into autoencoder neural network...

10 November 2016 1,073 8 View

How can I save rule sets generated from Genetic algorithm Intrusion Detection System ?

What is the best way to store rule sets generated from Genetic Algorithm for Intrusion Detection System (IDS) ? And how can this rule be used for testing new network traffic ?

31 December 2015 9,626 8 View

What are the research areas for computer networks ?

11 December 2015 9,175 26 View

How to compare two groups with only two measurements?

Hiiiii everyone! I have an enquiry on statistical analysis. I was looking for many forum and it's still cannot solve my problem. I want to compare means of two groups of data but only with two...

03 March 2021 8,796 3 View

Why should we choose deep learning to machine learning? Why is CNN better for image classification? Can I get Typical Answer?

What Characteristics makes CNN work better?

03 March 2021 1,458 4 View

What are some of the research gaps in machine learning and artificial intelligence in africa?

i would to know some of the research gaps in the artificial intelligence field in most african countries.

03 March 2021 6,145 3 View

Anyone plz suggest relevant topic for research in image processing+Deep learning.?

I have selected brain tumor images ...but now found that already lots of research done n this topic.

03 March 2021 5,774 3 View

What's the best way to measure growth rates in House sparrow chicks from day 2 to day 10?

What's the best way to measure growth rates in House sparrow chicks from day 2 to day 10? Since, the growth curve from day 2 to 10 won't be like the "Logistic curve" it might not follow logistic...

03 March 2021 1,401 3 View

How to increase a model accuracy ?

dear community, my model is based feature extraction from non stationary signals using discrete Wavelet Transform and then using statistical features then machine learning classifiers in order to...

03 March 2021 6,994 5 View

What is the production process of CaFe ferroalloys?

I looking for ferro calcium production process

03 March 2021 1,755 4 View

Can you share me how teacher education is managed in your respective national educational system?

I feel that the practice in teacher education in my country is below the expected performance level due to very poor management system. Hope I will learn something from your experiences.

02 March 2021 1,516 4 View

Can NFL theorem be valid in infinite search space in ML?

NFL theorem is valid for algorithms training in fixed training set. However, the general characteristic of algorithms in expanded or open dataset has not been proved yet. Could you show your...

01 March 2021 1,189 3 View

What is the difference between L1 and L2 regularization in machine learning?

L1 and L2 regularization

28 February 2021 4,187 3 View