Newest 'datasets' Questions

3

votes

1answer

48 views

Why different images of the same person, under some restrictions, are in a 50 dimension manifold?

In this lecture (starting from 1:31:00) the professor says that the set of all images of a person lives in a low dimensional surface (compared the the set of all possible images). And he says that the ...

asked Mar 3 at 10:19

Daviiid

1012 bronze badges

0

votes

0answers

18 views

Includes only some features of the dataset in a dataloader [closed]

I created a dataset and to creat a dataloader with Pytorch. I have the following problem, I would like to create a dataloader with only the features data and y_vector. As I apply torch.utils.data....

datasets pytorch data-preprocessing

asked Feb 26 at 17:18

Stefano Barone

1834 bronze badges

1

vote

0answers

18 views

Theoretical limits on correlation between classification algorithm performances

Are there any known theoretical bounds, or at least heuristic approaches, regarding the relation or correlation between the performances of any two different classification algorithms? For example, ...

machine-learning classification datasets

asked Feb 20 at 13:15

heron1000

111 bronze badge

2

votes

1answer

63 views

Would it be possible to determine the dataset a neural network was trained on?

Let's say we have a neural network that was trained with a dataset $D$ to solve some task. Would it be possible to "reverse-engineer" this neural network and get a vague idea of the dataset $...

neural-networks machine-learning datasets generative-model

asked Feb 12 at 8:37

sahal mulki

233 bronze badges

3

votes

1answer

51 views

How to treat (label and process) edge case inputs in machine learning?

In every computer vision project, I struggle with labeling guidelines for border cases. Benchmark datasets don't have this problem, because they are 'cleaned', but in real life unsure cases often ...

computer-vision classification datasets object-detection yolo

asked Feb 3 at 14:43

Huxwell

914 bronze badges

1

vote

1answer

55 views

What dataset might Elon Musk's Dall-E have used?

Dall-E, it can generate many imaginative images from the description, even some peculiar images, how did they actually create this kind of dataset to train this AI , because there is not much of that ...

natural-language-processing datasets generative-adversarial-networks image-generation natural-language-understanding

asked Jan 21 at 2:34

Gavin

393 bronze badges

2

votes

0answers

29 views

In few-shot classification, should I use my custom dataset as the validation dataset and mini-ImageNet as the training dataset?

I am new to few-shot learning, and I wanted to get a hands-on understanding of it, using Reptile algorithm, applied to my custom dataset. My custom dataset has 30 categories, with 5 images per ...

classification datasets meta-learning few-shot-learning reptile-algorithm

asked Jan 11 at 16:30

Geneveve08

312 bronze badges

4

votes

1answer

112 views

How should I generate datasets for a SARSA agent when the environment is not simple?

I am currently working on my master's thesis and going to apply Deep-SARSA as my DRL algorithm. The problem is that there is no datasets available and I guess that I should generate them somehow. ...

reinforcement-learning datasets environment sarsa on-policy-methods

asked Jan 6 at 7:26

Shahin

1534 bronze badges

1

vote

0answers

39 views

Is training on single game each time appropriate for an agent to learn to play checkers

I was facing a problem I mentioned in a previous question but after a while, I realize that maybe the problem in the dataset not in the learning rate. I build the dataset from white positions only i.e ...

machine-learning reinforcement-learning training datasets checkers

asked Jan 3 at 9:59

Kais Hasan

1747 bronze badges

0

votes

0answers

17 views

Where can a dataset of relationship between images be used?

I'm making a platform that will collect data about the relationship between different images. For example, if I have three images: a Christmas tree, a gift and Santa... then these will be connected by ...

datasets structured-data

asked Dec 23 '20 at 15:00

Shreyas Pradhan

1

vote

0answers

13 views

Is there a pre-trained network trained on RGB-D (4) channels? [closed]

The most used pre-trained networks for computer vision (e.g. ResNet50) are trained on 3 channels (RGB). At the same time, many cameras used in robotics return RGB-D outputs, that is including depth ...

computer-vision datasets reference-request pretrained-models

asked Dec 20 '20 at 21:15

Rexcirus

2511 silver badge6 bronze badges

2

votes

2answers

30 views

Why can't we combine both training and validation data, given that both types of data are used for developing the model?

Sorry if I sound confused. I read that data to be fed to a machine are divided into training, validation and test data. Both training and validation data are used for developing the model. Test data ...

machine-learning datasets

asked Dec 18 '20 at 6:00

user781486

1835 bronze badges

3

votes

1answer

72 views

Can we use ML to do anything else other than predicting (in the case of mathematical problems)?

(The math problem here just serves as an example, my question is on this type of problems in general). Given two Schur polynomials, $s_\mu$, $s_\nu$, we know that we can decompose their product into a ...

neural-networks deep-learning datasets math supervised-learning

asked Dec 16 '20 at 4:18

SmoothKen

512 bronze badges

0

votes

0answers

34 views

Is there any rule of thumb to determine the amount of data needed to train a CNN

I am training an AlexNet Convolutional Neural Network to classify images in a dataset. I want to know if there is any general rule for using data augmentation in training a neural network. How can I ...

deep-learning convolutional-neural-networks training datasets data-augmentation

asked Dec 15 '20 at 18:16

SahaTib

1308 bronze badges

2

votes

1answer

63 views

How robust are deep networks to class imbalance?

Before deep learning, I worked with machine learning problems where the data had a large class imbalance (30:1 or worse ratios). At that time, all the classifiers struggled, even after under-sampling ...

neural-networks deep-learning datasets data-preprocessing imbalanced-datasets

asked Dec 12 '20 at 6:30

user3667125

1,0301 silver badge8 bronze badges

0

votes

0answers

49 views

What could be a good $\mathcal{R}$ dataset in the article “Old Photo Restoration via Deep Latent Space Translation”?

There are three domains in this article: Old Photo Restoration via Deep Latent Space Translation. The real old pictures noted by $\mathcal{R}$, the artificial old pictures noted by $\mathcal{X}$, and ...

deep-learning datasets papers image-restoration

asked Dec 1 '20 at 17:08

Alex

1011 bronze badge

1

vote

1answer

55 views

Is it okay to think of any dataset in artificial intelligence as a mathematical set?

A dataset is a collection of data points. It is known that the data points in the dataset can repeat. And the repetition does matter for building AI models. So, why does the word dataset contain the ...

machine-learning datasets math definitions

asked Nov 28 '20 at 8:27

hanugm

3491 silver badge7 bronze badges

1

vote

1answer

57 views

Should we also shuffle the test dataset when training with SGD?

When training machine learning models (e.g. neural networks) with stochastic gradient descent, it is common practice to (uniformly) shuffle the training data into batches/sets of different samples ...

machine-learning training datasets stochastic-gradient-descent testing

asked Nov 3 '20 at 4:45

SpiderRico

5292 silver badges11 bronze badges

1

vote

1answer

44 views

What is the reason for taking tuples as vectors rather than points?

Across the literature of artificial intelligence, especially machine learning, it is normal to treat the tuples of datasets as vectors. Although there is a convention to treat them as data points. ...

machine-learning datasets terminology

asked Oct 27 '20 at 1:16

hanugm

3491 silver badge7 bronze badges

0

votes

0answers

31 views

Transforming neural network target values before training

Consider the scenario in which I am measuring certain $f(a,x)$, which i want to be the target value for some related input $g(a,x)$. In other words, I am trying to map $$g(a,x)\Rightarrow f(a,x)$$ I ...

neural-networks machine-learning datasets data-preprocessing imbalanced-datasets

asked Oct 25 '20 at 11:49

Thomas Wagenaar

9975 silver badges10 bronze badges

0

votes

1answer

54 views

Is it possible to know the distance objects are from camera based on only knowing one object's height?

I am doing a project where I have to know distance a particular object is from camera. In the photo I only know one of the object's height, but I don't know how far away that object is and I don't ...

neural-networks convolutional-neural-networks datasets math

asked Oct 13 '20 at 14:27

Artūras Drūteika

11

1

vote

0answers

29 views

How to find distance between 2 points when dimensions are all of different nature?

I have a dataset with four features: the x coordinate the y coordinate the velocity magnitude angle Now, I want to measure the distance between two points in the dataset, taking into account the ...

datasets loss-functions linear-algebra

asked Oct 3 '20 at 18:33

Manish Kausik Hari Baskar

634 bronze badges

0

votes

0answers

31 views

Multi-label dataloading bottleneck Pytorch

I am trying to write custom dataset and dataloader for pascal-voc-2007. It is a multi-label classification problem. There is csv file to hold the name of the images and their corresponding labels. I ...

deep-learning datasets pytorch

asked Sep 29 '20 at 22:01

ikadorus

211 bronze badge

1

vote

0answers

54 views

Which loss function to choose for imbalanced datasets?

For imbalanced datasets (either in the context of computer vision or NLP), from what I learned, it is good to use a weighted log loss. However, in competitions, the people who are in top positions are ...

deep-learning datasets loss-functions

asked Sep 19 '20 at 12:23

Ravi Teja

512 bronze badges

1

vote

1answer

65 views

What are some examples of functions that machine learning models compute?

My simple understanding of AI is that it is based on a mathematical model of a problem. If I understood correctly, the model is a polynomial equation and its weights are calculated by training the ...

machine-learning training datasets models weights

asked Sep 15 '20 at 10:19

scico111

1132 bronze badges

0

votes

1answer

23 views

Can a neural network be trained on a dataset containing only values for true output for a classification problem?

I am using a dataset from Google which contains 1,27,000 data points on simulated concentrations of the atmosphere of exoplanets which can sustain life. So, the output label of all these data points ...

neural-networks deep-learning classification datasets data-preprocessing

asked Sep 15 '20 at 7:26

Niranjan Dindodi

133 bronze badges

1

vote

0answers

42 views

Could the neural network automatically calculate and get different one-to-many quantities relative to their parent quantity?

Let's say I have a primary dataset that its secondary dataset is hundreds to match and group like an one-to-many relationship. I'm new in this world of the AI but my problem is that many child groups ...

neural-networks datasets math

asked Sep 14 '20 at 3:52

victcdva

114 bronze badges

3

votes

2answers

92 views

Can we use genetic algorithms to evolve datasets?

Genetic algorithms are used to solve many optimization tasks. If I have a dataset, can I evolve it with a genetic algorithm to create an evolved version of the same dataset? We could consider each ...

datasets genetic-algorithms genetic-operators

asked Sep 12 '20 at 2:54

Souradip Roy

312 bronze badges

1

vote

1answer

48 views

How can I classify houses given a dataset of houses with descriptions?

I have a dataset with a number of houses, for each house, I have a description. For example "The house is luxuriously renovated" or "The house is nicely renovated". My aim is to ...

natural-language-processing classification datasets

asked Aug 30 '20 at 21:21

Melly Donald

354 bronze badges

0

votes

0answers

32 views

Can I use the full dataset for training the CNN feature extractor?

I built a CNN model for extracting features from its dense layer. The extracted features are then used for classification using KNN and Random Forest classifier. My question is, can I use the whole ...

machine-learning convolutional-neural-networks datasets feature-extraction

asked Aug 21 '20 at 20:02

Hardik Gunjal

11 bronze badge

0

votes

0answers

9 views

Quality of synthetic sample and corresponding label generated by SMOTE or ADASYN?

When SMOTE or ADASYN create synthetic sample and the corresponding label, is the quality of the label trust worthy OR should I should double check the label by myself ? Particularly in a ...

datasets

asked Aug 20 '20 at 7:14

Tuong Nguyen Minh

1233 bronze badges

0

votes

0answers

28 views

How should I label images to get high accuracy with YOLO?

I am new to Object Detection with Yolo and I have questions regarding the labeling (for custom objects): Is there any guideline or tips on how to label images to have high accuracy at the end? ...

computer-vision image-recognition datasets object-detection yolo

asked Aug 17 '20 at 16:28

can.inan

1

0

votes

0answers

19 views

Conditional GAN on harder datasets

I have seen conditional GANs often applied to easier datasets like MNIST and CIFAR-10 to reasonable success, but at the same time these datasets are simple enough that naïve CNNs can fairly easily max ...

convolutional-neural-networks datasets generative-adversarial-networks

asked Aug 14 '20 at 20:42

Alekxos

1213 bronze badges

0

votes

0answers

23 views

Can I train an object detection model with images with a white background?

To be more specific I have a dataset of 2400 images with unbalanced classes, 1 object per image and sometimes some objects are repeated along the dataset but in a different position and rotation of ...

computer-vision datasets object-detection

asked Aug 7 '20 at 1:57

Bernardo Costa

13 bronze badges

1

vote

1answer

313 views

How to generate labels for self-supervised training?

I've been reading a lot lately about self-supervised learning and I didn't understand very well how to generate the desired label for a given image. Let's say that I have an image classification task, ...

deep-learning datasets supervised-learning self-supervised-learning feature-learning

asked Aug 4 '20 at 8:34

Vesko Vujovic

1813 bronze badges

0

votes

0answers

103 views

Multilabel stratified split for images/object detection

I am working on an object detection model and have thought of looking into stratified splits for the dataset. Now since I am doing object detection I have a variable number of "labels" for ...

datasets data-preprocessing

asked Jul 30 '20 at 6:06

Rares Dima

1011 bronze badge

3

votes

2answers

75 views

How can I predict the true label for data with incomplete features based on the trained model with data with more features?

Suppose I have a model that was trained with a dataset that contains the features (f1, f2, f3, f4, f5, f6). However, my test dataset does not contain all features ...

machine-learning deep-learning training datasets testing

asked Jul 23 '20 at 10:44

Dae-Young Park

311 bronze badge

0

votes

0answers

52 views

Can I train a neural network with multiple datasets (e.g. 25)?

I want to create a neural network that I can train with many datasets (e.g. 20 - 25 datasets). Can I use transfer learning for this? Or is there a better approach than this?

neural-networks deep-learning datasets transfer-learning

asked Jul 23 '20 at 2:05

Mikul Rai

113 bronze badges

2

votes

0answers

43 views

How can I formulate a prediction problem (given labeled data) as an RL problem and solve it with Q-learning?

One of my friends sent me a problem he was working on lately, and I couldn't help but I wonder how could it be solved using Q-learning. The statement is as follows: Given the following datasets, the ...

reinforcement-learning ai-design q-learning datasets

asked Jul 11 '20 at 19:13

Conny

211 bronze badge

3

votes

1answer

100 views

Is it possible to classify resistors using ResNet50?

I want to train ResNet50 model using resistor images like below: I tried it by collecting data from google images and there were quite few. So accuracy was very low (around %10) but I wonder If it is ...

deep-learning classification computer-vision datasets categorical-data

asked Jul 3 '20 at 14:41

Nabla

1824 bronze badges

0

votes

0answers

28 views

accessible subset of data impacts performance

I have a problem with a subset of my data which is as follows: I can train a model (doesn't matter what, xgboost, BERT, etc., it is a text classification problem), on my data and get a decent ...

classification datasets text-classification importance-sampling

asked Jul 2 '20 at 12:45

N. Kiefer

2464 bronze badges

1

vote

0answers

22 views

How is the performance of a CNN trained with monochrome images on image recognition tasks degraded?

For CNN image recognition tasks, like object recognition/face recognition/object segmentation/posture recognition, are there experiment results about how much will the performance be degraded with ...

convolutional-neural-networks datasets reference-request data-preprocessing performance

asked Jun 24 '20 at 8:00

jw_

1814 bronze badges

1

vote

1answer

32 views

How to split data into training validation and test set when the number of data in classes varies greatly?

I have 5 classes of pictures to classify: 0 -> ~3 200 (~800 initial number before interference and duplication) 1 -> ~9 000 (I reduced from ~90 000) 2 -> ~8 000 3 -> ~3 000 4 -> ~7 200 How to ...

deep-learning classification training datasets

asked Jun 16 '20 at 7:40

Dominik Sie

558 bronze badges

2

votes

0answers

26 views

How does sampling works in case of imbalanced image datasets?

I am solving a problem of image classification of the image dataset for 3 classes. Dataset is highly imbalanced. How will sampling (either over- or under-sampling) work in that case? Should I remove (...

deep-learning convolutional-neural-networks classification datasets data-preprocessing

asked May 18 '20 at 21:18

Mark

1211 bronze badge

2

votes

1answer

71 views

Is this dataset with only two features suitable for clustering with k-means?

I am working with the K-means clustering algorithm for unsupervised learning. Is the following dataset suitable for the k-means clustering task or not? Why or why not? The dataset has only two ...

datasets unsupervised-learning data-science clustering k-means

asked May 17 '20 at 22:31

Debugger

612 bronze badges

4

votes

1answer

98 views

How to fill missing values in a dataset where some properties can be inputs and outputs?

I have a dataset with missing values, I would like to use machine learning methods to fill. In more detail, there are $n$ individuals, for which up to 10 properties are provided, all numerical. The ...

machine-learning datasets data-preprocessing

asked May 14 '20 at 20:56

Smerdjakov

935 bronze badges

2

votes

0answers

37 views

Why is ANFIS important in general?

I am actually working with the iris dataset from sklearn and try to understand the ANFIS-Package for python. But that does not really matter! I have a more general question. During thinking about ...

neural-networks machine-learning datasets

asked May 14 '20 at 9:37

Eli Hektor

411 bronze badge

1

vote

0answers

27 views

How can raw data from a motion sensor (like an IMU) reduced to the main points of the data

How can I reduce the caputured movement data of a person in a way, that I have filtered the main features of the movement. Or how can I detect pattern/ main features in that data set? I captured some ...

datasets data-preprocessing

asked May 6 '20 at 13:31

MScott

3952 silver badges8 bronze badges

1

vote

0answers

14 views

What are the best datasets available for music information retrieval?

I am interested in doing some work in classification problems in music information retrieval. I know that there are some formats of datasets (such as MIDI, Spectrogram, Piano-roll, MusicXML, etc.) for ...

natural-language-processing datasets data-science audio-processing structured-data

asked May 1 '20 at 6:07

Siddharth Bachoti

1111 bronze badge

0

votes

0answers

24 views

dataset structure for context aware task-oriented dialogue systems

I have been reading papers on Dialog State Tracking and Intent Detection and Slot Filling for building a simple ...

natural-language-processing datasets dialogue-systems

asked Apr 28 '20 at 15:02

greedsin

1111 bronze badge

Questions tagged [datasets]

Related Tags