Questions tagged [dimensionality-reduction]

For questions related to AI methods of dimensionality reduction (e.g. PCA or autoencoders).

Filter by
Sorted by
Tagged with
11
votes
4answers
3k views

What are the purposes of autoencoders?

Autoencoders are neural networks that learn a compressed representation of the input in order to later reconstruct it, so they can be used for dimensionality reduction. They are composed of an encoder ...
5
votes
2answers
75 views

What are examples of approaches to dimensionality reduction of feature vectors?

Given a pre-trained CNN model, I extract feature vector of images in reference and query dataset with several thousands of elements. I would like to apply some augmentation techniques to reduce the ...
3
votes
1answer
114 views

How do AI researchers imagine higher dimensions?

We can visualize single, two, and three dimensions using websites or imagination. In the context of AI and, in particular, machine learning, AI researchers often have to deal with multi-dimensional ...
3
votes
1answer
55 views

When using PCA for dimensionality reduction of the feature vectors to speed up learning, how do I know that I'm not letting the model overfit?

I'm following Andrew Ng's course for Machine Learning and I just don't quite understand the following. Using PCA to speed up learning Using PCA to reduce the number of features, thus lowering the ...
3
votes
0answers
18 views

What is meant by subspace clustering in MFA?

The basic idea of MFA is to perform subspace clustering by assuming the covariance structure for each component of the form, $\Sigma_i = \Lambda_i \Lambda_i^T + \Psi_i$, where $\Lambda_i \in \mathbb{R}...
2
votes
1answer
150 views

Why does PCA of the vertices of a hexagon result in principal components of equal length?

I do PCA on the data points placed in the corners of a hexagon, and get the following principal components: The PCA variance is $0.6$ and is the same for each component. Why is that? Shouldn't it be ...
2
votes
0answers
45 views

Estimating dimensions to reduce input image size to in CNNs

Considering input images to a CNN that have a large dimension (e.g. 256X256), what are some possible methods to estimate the exact dimensions (e.g. 16X16 or 32X32) to which it can be condensed in the ...
2
votes
0answers
27 views

Compressing Parameters of an Response System

I have an input-output system, which is fully determined by 256 parameters, of which I know a significant amount are of less importance to the input-output pattern. The data I have is some (64k in ...
2
votes
2answers
85 views

How can I use autoencoders to analyze patterns and classify them?

I generated a bunch of simulation data from a complex physical simulation that spits out patterns. I am trying to apply unsupervised learning to analyze the patterns and ideally classify them into ...
2
votes
0answers
21 views

Clustering of very high dimensional data and large number of examples without losing info in dimensions

I'm trying to get a grasp on scalability of clustering algorithms, and have a toy example in mind. Let's say I have around a million or so songs from $50$ genres. Each song has characteristics - some ...
1
vote
1answer
35 views

How classification neural nets are different from simple dimension reduction + clustering?

I know the training of neural nets involves some sort of dimension manipulation to separate classes of different features. If there is no variation of features, no matter for neural nets or simple ...
1
vote
0answers
54 views

How to cluster data points such that the number of clusters is kept minimal and each cluster projects well onto a lower-dimensional subspace?

If I want to find a (linear) subspace onto which a data-set projects well, I can simply use PCA. However, often the data can project with much smaller error if I first separate it into a couple of ...
0
votes
1answer
26 views

How does t-SNE preserves embedding orders?

According to the triplet loss Wikipedia page: t-SNE (t-distributed Stochastic Neighbor Embedding) preserves embedding orders via probability distributions, whereas triplet loss works directly on ...
0
votes
0answers
38 views

Deep Continuous Clustering algorithm - just one output cluster

I use the DCC algorithm to cluster some data. The whole algorithm is available here, but shortly it is: construct mkNN graph of the data points (the connected components of it are the clusters). ...
0
votes
0answers
31 views

How to deal with large number of features for Anomaly Detection

I am trying to build anomaly detection with low false positives .Dataset that i am using is a patient health sensor data. A number of parameters from the patient's sensors are collected hourly and I ...