Skip to main content
OverflowAI is here! AI power for your Stack Overflow for Teams knowledge community. Learn more
5 votes
Accepted

What are bag-of-features in computer vision?

Introduction Bag-of-features (BoF) (also known as bag-of-visual-words) is a method to represent the features of images (i.e. a feature extraction/generation/representation algorithm). BoF is inspired ...
nbro's user avatar
  • 40.8k
5 votes
Accepted

What is "conditioning" on a feature?

This is conditioning in the sense of conditional probability. The idea is that the authors have some "standard physically-inspired features". They are splitting the data up into bins based on the ...
John Doucette's user avatar
5 votes
Accepted

Does the correlation between inputs affect the model performance?

Non-correlation does not imply independence, that is, if two features are not correlated (i.e. zero correlation), it does not mean that they are independent. But (non-zero) correlation implies ...
nbro's user avatar
  • 40.8k
5 votes
Accepted

What is the difference between features and inputs in machine learning?

An input usually refers to an example (sometimes also known as sample, observation or data point) $x$ from a dataset that you pass to the model. For example, in supervised learning, you have a ...
nbro's user avatar
  • 40.8k
4 votes

How to design a neural network that gets the author name of a piece of art as input?

The most straightforward approach I would recommend would be the one-hot encoding solution without a feature for ''other author''. If you use drop-out during training, the network should learn how to ...
Dennis Soemers's user avatar
  • 10.3k
4 votes

How to convert color information to 1D feature vector?

My 2 suggestions would be to: Sum the hex coding of the color multiplied by the prevalence. For example [80, 80, 80] (grey) is used 7% of the time so ...
Kroshtan's user avatar
  • 259
3 votes
Accepted

How to add more features to the input of a machine learning algorithm?

Data pre-processing and feature extraction are by far the most important part of any machine learning algorithm. It's even more important that the model you choose to do the classification. ...
JahKnows's user avatar
  • 470
3 votes

How to design a neural network that gets the author name of a piece of art as input?

I would try to find some proxy features about the author, as opposed to encode the identity of the author. Likely good features of an author include averages of other features about the work (such as ...
Neil Slater's user avatar
  • 32.4k
3 votes

How can a neural network distinguish a rotated 6 and 9 digits?

I think by writing left to right people create clockwise and counterclockwise patterns in the rounded parts of their typography. For example, I think it'd be pretty unusual to write a 9 like this --&...
waxalas's user avatar
  • 99
3 votes

How to convert color information to 1D feature vector?

I think the tool you found is useful for a human and to get nice visuals but I also think it's totally useless for feature extraction. If you want to pass explicit information about colors simply ...
Edoardo Guerriero's user avatar
2 votes
Accepted

How to handle varying types and length of inputs in a feedforward neural network?

In short ANNs don't have problems with "different types" of data as long as they are represented using real numbers: the inputs for your ANN represent lengths and are easy to understand and ...
Alvin Sartor's user avatar
2 votes
Accepted

What is a temporal feature?

In general, the expression "temporal feature" might refer to any feature that is associated with or changes over time. However, in the context of signal processing, a temporal feature might ...
nbro's user avatar
  • 40.8k
2 votes
Accepted

If I wanted to calculate multiple feature maps in a convolutional layer, should the filters be trained individually?

Each feature map (or kernel) is independent of each other. If you had $3$ of these filters, your output shape would be $(28, 28, 3)$ (given the appropriate amount of padding and stride) with a total ...
mshlis's user avatar
  • 2,369
2 votes

Do the eigenvectors represent the original features?

The principal components (eigenvectors) correspond to the direction (in the original n-dimensional space) with the greatest variance in the data. The corresponding eigenvalue is a number that ...
Dunk's user avatar
  • 121
2 votes
Accepted

When is adding a feature useless?

Now I want to check if I can predict B directly from A, since, in my understanding, this would mean that info on B is already inside A. This will help inform you how much redundancy there is between ...
Neil Slater's user avatar
  • 32.4k
2 votes
Accepted

How do we know that the neurons of an artificial neural network start by learning small features?

We do it experimentally; you're able to look at what each layer is learning by tweaking various values throughout the network and doing gradient ascent. For more detail, watch this lecture: https://...
Recessive's user avatar
  • 1,396
2 votes
Accepted

Does feature scaling have any benefits if all features are on the same scale?

If all you features are binary, then, you don't need to apply normalization on them. Since their values are on the same scale already.
Abhishek Verma's user avatar
2 votes

How are small scale features represented in an Inverse Graphics Network (autoencoder)?

Simply said, there is no specific "meaning" to the features generated. They are simply features that are fitted through math and calculus, and nobody knows what they represent exactly, and will never ...
Clement's user avatar
  • 1,745
2 votes

When is it necessary to manually extract features to feed into the neural network rather than providing raw data?

Feature engineering may be necessary when one cannot achieve acceptable error rate — within a budget or in principle. NN may be stalling due to information bottleneck: too many pigeons, not enough ...
ShadowsInRain's user avatar
2 votes
Accepted

When is it necessary to manually extract features to feed into the neural network rather than providing raw data?

Yes, neural networks learn features themselves freeing you from the need to manually engineer them. I will illustrate it here with a toy problem. Let's assume that we want to learn the areas of ...
Vladislav Gladkikh's user avatar
2 votes
Accepted

Can I always interpret features as random variables in machine learning safely?

In general terms yes. Because what the ML algorithms do in general is to learn the hidden probability density function of the target examples (cats, dogs..). And that is done by learning the ...
JVGD's user avatar
  • 1,138
2 votes

Is it true that channels always represent colours of an image?

No, channels do not have to only represent colours. It is common for them to represent other things, even without considering feature maps. For instance RGBD images, where D is a depth measurement or ...
Neil Slater's user avatar
  • 32.4k
2 votes
Accepted

How to calculate a meaningful distance between multidimensional tensors

You could try an earth mover distance in 2d or 3d over the image? For example you could follow this example, but call it sequentially. The idea would be something like the following (untested and ...
John St. John's user avatar
2 votes
Accepted

Is there any advantage to providing multi-dimensional input to torch modules?

Yes, for some applications, the spatial component of the tensor is indeed very important, but not for the examples you mentioned. The first point to clarify is that even though the ...
Cesar Ruiz's user avatar
1 vote

How do we know that the neurons of an artificial neural network start by learning small features?

The network architecture is relevant to this question. Convolutional neural network architectures enforce the building up of features because the neurons in earlier layers have access to a small ...
user7834's user avatar
1 vote

Does the weight vector form imply feature space curvature?

No, it does not take into account the curvature. But, if curvature is important for you, then, it would be a good idea to look at Ricci flow and its applications in neural networks.
Abhishek Verma's user avatar
1 vote

How to predict the best from a set of messages - best practice

One way you can definitely approach the problem is by using (Deep) Reinforcement Learning (DRL). YouTube is actually using DRL as well to suggest videos to users in order to maximize users' engagement ...
Daniel B.'s user avatar
  • 825
1 vote

Is it possible to flip the features and labels after training a model?

The body of your post seems to be asking a completely separate question than the title of your post, so I will answer both: "Body: How do I complete the goal of this program?" Your dataset ...
user3667125's user avatar
  • 1,570
1 vote

Feature scaling strategy for many feature with very large variation between them?

You should normalize every column individually. It will work just fine. Sum up the column and divide every element of that column by sum of that column. But as your feature 2,3,4 are of very small ...
SrJ's user avatar
  • 126
1 vote

Feature scaling strategy for many feature with very large variation between them?

You should check the distribution of each feature and scale them accordingly, but in any case you should aim to roughly the same interval of values for every feature. For example, if f1 has the ...
oleg.mosalov's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible