Questions tagged [features]
For questions related to features in the context of machine learning and, in general, AI.
59
questions
1
vote
1
answer
50
views
Is there any advantage to providing multi-dimensional input to torch modules?
Most layer types in torch.nn such as torch.nn.Linear accept input with more than one dimension. Is there any advantage in doing so if you can shape your data to represent a certain arrangement in ...
0
votes
0
answers
20
views
From Text-To-Speech to LLMs: Providing "writing style"
I've just recently learned about Text-To-Speech models and how they are trained. Unlike LLMs, to a provided pair (text, speech), a feature vector ${f}$, that was generated by more speech of that ...
1
vote
1
answer
37
views
Feature vector representation of probability distribution
I have a series of multiple probability distribution like this:
[
[0.2, 0.3, 0.5],
[0.1, 0.2, 0.7],
...
]
Do you have any suggestions how I can represent this ...
0
votes
0
answers
7
views
How can I normalize features while preserving information about the original values?
I am trying to feed a neural network stock prices of an instrument. To ensure training stability, I normalize the inputs to have mean=0 and std=1.
However, I thought that for stock prices, the ...
1
vote
1
answer
53
views
Transfer Learning for Solar Energy Production Forecasting with LSTM: Generalized vs. Specialized Models
I am working on a solar energy production forecasting problem using LSTM multi-step models to predict 1/4/8h ahead of solar energy production for different solar installations. Our goal is to help ...
1
vote
1
answer
43
views
Features for a Content-Based recommendation system
I'm working on a hybrid recommendation system (collaborative and content-based) for an online ordering/shopping app. So far I've managed to identify a data-source for the collaborative model (likely ...
1
vote
0
answers
60
views
Understanding the features given in Example 13.1 of Sutton and Barto
I'm struggling to understand the notation used to represent the features within Example 13.1 (Short corridor with switched actions" in the Sutton and Barto RL book.
I assume as it is a free pdf ...
1
vote
0
answers
35
views
Why "Good Model" that performs great on holdout validation data fails on production data
I have this binary regression model that has ~500 futures with an unbalanced dataset with the following results.
...
1
vote
1
answer
182
views
How to handle out-of-bound values in Production data?
So I have this model but the data may vary. And it is virtually impossible to always have the values in bounds. If I do I`d have to use larger period leading to concept shift which is worse.
The ...
2
votes
1
answer
491
views
How to calculate a meaningful distance between multidimensional tensors
TLDR: given two tensors $t_1$ and $t_2$, both with shape $(c,h,w),$ how shall the distance between them be measured?
More Info: I'm working on a project in which I'm trying to distinguish between an ...
4
votes
2
answers
55
views
Is there any proper literature on the types of features that different layers of a deep neural network learn?
Let's consider a deep convolutional network. It seems that there is some consensus on the following notions:
1. Shallow layers tend to recognise more low-level features such as edges and curves.
2. ...
2
votes
2
answers
387
views
How to convert color information to 1D feature vector?
We are making a classification model that takes a clip of a movie as an input and predicts who the director is. Roughly speaking, it will be a model that understands film directors' unique style.
We ...
2
votes
2
answers
3k
views
What is the difference between features and inputs in machine learning?
I have seen many places that features and inputs have been used interchangeably when talking about machine learning especially deep neural networks. I want to know if they are indeed the same thing or ...
1
vote
1
answer
559
views
What kind of features does each node have as an input graph to a graph neural network?
What kind of features does each node have as an input graph to a graph neural network? For example, we want to do image classification with GNN, what are the features of each pixel? Or if anyone could ...
1
vote
1
answer
58
views
What is the name of a feature space which has consistant distance-related properties?
What is the word describing a feature space where distance between two elements has a decisive informational value, whatever the pair of elements is?
For example if a model creates embeddings for ...
1
vote
1
answer
191
views
When is it appropriate to use information like sex or race in ethical machine learning?
I'm a little confused on best practices regarding ethical ML. Specifically, I've seen in some courses that when building a model that affects people, it's helpful to have sensitive personal ...
0
votes
0
answers
49
views
Does it make sense to compare images (samples) with words (features)?
Consider the following paragraphs from the introduction of the chapter named Recurrent Neural Networks from the textbook titled Dive into Deep Learning
So far we encountered two types of data: ...
1
vote
0
answers
88
views
What do state features mean in the context of inverse RL?
I am reading Zeibart's Inverse RL paper, and it states -
The agent is assumed to be attempting to optimize some function that linearly maps the features of each state, $f_{sj} \in \mathbb{R}^k$, to a ...
1
vote
0
answers
33
views
What is the difference between the $Q_a$ calculated to update delta and those to select next action in the exploitation phase?
As the title suggests, I have a doubt about the computation of the $Q_a$ used to update the delta and the $Q_a$ used to select the next action in the exploitation phase, as shown below (source of ...
7
votes
2
answers
289
views
How can a neural network distinguish a rotated 6 and 9 digits?
Rotated MNIST is a popular dataset for benchmarking models equivariant to rotations on $\mathbb{R}^2$, described by $SO(2)$ group or its discrete subgroups like $\mathbb{Z}^{n}$:
Group equivariant ...
0
votes
1
answer
478
views
When can we call a feature "hierarchical"?
Features in machine learning are the attributes of the elements of a data set. They are considered as random variables in probability.
Consider the following excerpt from 1.1: The deep learning ...
2
votes
1
answer
380
views
Is it true that channels always represent colours of an image?
Convolutional neural networks are widely used in image-related tasks in artificial intelligence.
The input of a conventional neural network is generally an image. The output of a convolutional neural ...
2
votes
1
answer
902
views
What are examples of node 'features' in graph networks?
Context: I was reading Chapter 3 in the following book (here) about graph representation learning. Before I get to node embeddings, I wanted to make sure that I do understand what is meant by the ...
0
votes
1
answer
598
views
How to find "relationships" between two data representations?
I am a researcher in a field, and new to the whole of AI and machine learning techniques. May the following question is trivial or not framed in the ML language but I try my best.
I have two sets of ...
1
vote
0
answers
766
views
What does it mean by "low-level" and "high-level" in features generated by CNN?
Across the literature, the terms "high-level" and "low-level" are generally used as an adjective to the features generated by the convolution neural network as intermediate ...
0
votes
1
answer
75
views
Why disentangling the features of variation in representation?
Consider the following excerpt from abstract of the research paper titled Better Mixing via Deep Representations by Yoshua Bengio et al.
It has been hypothesized, ...
1
vote
1
answer
327
views
Can I always interpret features as random variables in machine learning safely?
Consider the following statements from Chapter 5: Machine Learning Basics from the book titled Deep Learning (by Aaron Courville et al.)
Machine learning tasks are usually described in terms of how ...
1
vote
0
answers
260
views
How to train a machine learning model with multiple attributes and one target value?
I'm working on a machine learning problem where I need to guess which customers will churn and which of them will continue to be customers.
I have $X_0, X_1, X_2, X_3, X_4, X_5$ and $X_6$ attributes ...
4
votes
2
answers
885
views
When is it necessary to manually extract features to feed into the neural network rather than providing raw data?
Usually, Neural Networks uses raw data. You do not need to extract features manually. NN's can find & extract good features which is a pattern of an image, signal or any kind of data. When we ...
3
votes
2
answers
111
views
How do we know that the neurons of an artificial neural network start by learning small features?
I'd like to ask you how do we know that neural networks start by learning small, basic features or "parts" of the data and then use them to build up more complex features as we go through ...
1
vote
1
answer
49
views
Does feature scaling have any benefits if all features are on the same scale?
By scaling features, we can prevent one feature from dominating the decisions of a model. For example, say heights (cm), and age (years) are two features in my data. Since range of heights is larger ...
2
votes
1
answer
63
views
Does the weight vector form imply feature space curvature?
I came across this sentence when exploring a simple nearest neighbor classifier method using Euclidean distance (link):
The slightly odd thing about using the Euclidean distance to compare features ...
1
vote
1
answer
92
views
How to predict the best from a set of messages - best practice
Suppose I have a set of messages A,B,C,D and I want to produce the best message for a website user at a given time.
For training I plan to show random users a random single message [A/B/C/D] and fill ...
0
votes
1
answer
60
views
Is it possible to flip the features and labels after training a model?
The goal of this program is to predict a game outcome given a game-reference-id, which is a serial number like so:
id,totalGreen,totalBlue,totalRed,totalYellow,...
1
vote
2
answers
3k
views
What does the depth of a decision tree depend on?
In these notes, we have the following statement
The depth of a learned decision tree can be larger than the number of training examples used to create the tree
This statement is false, according to ...
0
votes
1
answer
495
views
What is the impact of the number of features on the prediction power of a neural network?
What is the impact of the number of features on the prediction power of an ANN model (in general)? Does an increase in the number of features mean a more powerful prediction model (for approximation ...
1
vote
1
answer
84
views
When is adding a feature useless?
I'm building a model, where, from a feature set A, I want to predict a target set C. I need to understand if another feature set B, together with A, can improve my model performances, instead of using ...
1
vote
2
answers
62
views
Feature scaling strategy for many feature with very large variation between them?
I was running into a situation in which my input feature experience a very large variation in term of magnitude.
Particularly, consider feature 1 belong to group 1 and feature 2 3 4 belong to group 2,
...
4
votes
1
answer
6k
views
What are bag-of-features in computer vision?
In computer vision, what are bag-of-features (also known as bag-of-visual-words)? How do they work? What can they be used for? How are they related to the bag-of-words model in NLP?
2
votes
2
answers
136
views
Can we train the model to detect real users with only positive labels?
We have hundreds of thousands of customers records, and we need to take the benefits of our data to train a model that will recognize fake entries or unrealistic ones for our platform, where customers ...
3
votes
1
answer
69
views
How are small scale features represented in an Inverse Graphics Network (autoencoder)?
This post refers to Fig. 1 of a paper by Microsoft on their Deep Convolutional Inverse Graphics Network:
https://www.microsoft.com/en-us/research/wp-content/uploads/2016/11/kwkt_nips2015.pdf
Having ...
5
votes
0
answers
68
views
Training and inference for highly-context-sensitive information
What is the best way to train / do inference when the context matters highly as to what the inferred result should be?
For example in the image below all people are standing upright, but because of ...
5
votes
1
answer
2k
views
What is "conditioning" on a feature?
On page 98 of Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning the author writes;
Redacted phase space: Studying the distribution of inputs ...
3
votes
1
answer
77
views
Do the eigenvectors represent the original features?
I've got a test dataset with 4 features and the PCA produces a set of 4 eigenvectors, e.g.,
...
0
votes
1
answer
85
views
What is the correct name for state explosion from sensor discretization?
The position of a robot on a map contains of an x/y value, for example $position(x=100.23,y=400.78)$. The internal representation of the variable is a 32bit float which is equal to 4 byte in the RAM ...
1
vote
0
answers
85
views
How can I use gradient boosting with multiple features?
I'm trying to use gradient boosting and I'm using sklearn's GradientBoostingClassifier class.
My problem is that I'm having a data frame with 5 columns and I want ...
1
vote
1
answer
71
views
When doing binary classification with neural networks, how can I order the importance of the features for a class?
I have a simple neural network for binary classification.
The input features include age, sex, economic situation, illness, disability, etc. The output is simply 1 and 0.
I would like to order the ...
2
votes
0
answers
84
views
Does coarse coding with radial basis function generate fewer features?
I am learning about discretization of the state space when applying reinforcement learning to continuous state space. In this video the instructor, at 2:02, the instructor says that one benefit of ...
2
votes
1
answer
304
views
If I wanted to calculate multiple feature maps in a convolutional layer, should the filters be trained individually?
Assume I have an input of size $32 \times 32 \times 3$ and pass it to a convolution layer. Now, if my kernel size were to be $5 \times 5 \times 3$ and the depth of my convolution layer were to be 1, ...
2
votes
2
answers
553
views
Is the number of feature maps equal to the number of kernels in the LeNet 5 architecture?
In LeNet 5's first layer, the number of feature maps is equal to the number of kernels. However, the second convolutional layer has a depth different from the 3rd layer. Does the filter size dictate ...