Questions tagged [datasets]

For questions related to sets of data and their use in AI.

Filter by
Sorted by
Tagged with
0 votes
1 answer
30 views

What are possible reasons for the validation loss increasing with more data?

I trained a neural network on an NLP problem and compared the loss and BLEU score on the validation data with the same training parameters in two scenarios: a) when I trained on 25% of the data, b) ...
1 vote
2 answers
55 views

Is data useless for a neural network if some inputs are derivatives of other inputs?

That is, if some of the inputs to a neural network can be calculated by a pre-determined function whose variables are other inputs, then are those specific inputs useless? For example, suppose there ...
1 vote
0 answers
39 views

How to get ZINC 500k dataset?

I have been using the ZINC graph regression dataset available through pytorch geometric datasets for a while now in two of its modes (12k examples and 250k examples). However, in the PapersWithCode ...
  • 191
0 votes
0 answers
24 views

How to organize data for training a neural network to raytrace images

I am trying to train a neural network to go from a series of numbers(data about a 3D scene, such as camera position, sphere position, radius, and color, etc) to a raytraced image. I can generate as ...
  • 1
1 vote
1 answer
56 views

How can imitation learning data be collected?

How can imitation learning data be collected? Can I use a neural network for that? It might be noisy. Should I use manual gathering?
0 votes
1 answer
2k views

Fine-tune GPT-Neo with prompt and completion?

I'm new to AI and machine learning. To fine-tune GPT-3, I understand that we need a set of training examples that each consist of a single input ("prompt") and its associated output ("...
  • 101
0 votes
0 answers
35 views

Do Neural Networks tend to have Zero Mean Errors in each Output?

My NN (a few linear layers with ReLUs + batch normalization, no activation in the last layer) learns to approximate vector-valued labels $y_z$ from data $z\sim\rho_z$ in a supervised way, i.e. net$(z)=...
  • 101
0 votes
1 answer
427 views

Split dataset into Train/Validation/Test for Object Detection

I have a dataset for Object Detection with YOLO format labels, each imagine can have occurences of different classes and multiple occurences of the same class. How can the dataset be divided into ...
0 votes
0 answers
9 views

What are common benchmarks (simulators and datasets) for testing compositionally in the visual domain?

Learning an object decomposition from a visual scene is a difficult problem for language models describing the scene, for radiance fields that reconstruct the scene, and also for generative models ...
10 votes
2 answers
1k views

How can I encode angle data to train neural networks?

I am training a neural network where the target data is a vector of angles in radians (between $0$ and $2\pi$). I am looking for study material on how to encode this data. Can you supply me with a ...
1 vote
1 answer
47 views

Can independent datasets be artificially combined for multimodal learning (semi-synthetic data generation)?

BACKGROUND: To apply multimodal machine learning (ML), the various data modalities typically come from the same example (e.g., chest X-ray (modality 1) and ...
2 votes
1 answer
53 views

Are the "artifacts" in select Keras MNIST training images really there or is my download corrupt?

I'm having fun with a ludicrously well known and used dataset: mnist. I am doing it with a huge and well known tool: keras. Please excuse the red dots, something else I was doing. I have otherwise ...
0 votes
1 answer
61 views

Why does data augmentation using synthetic data generated by one model improve the performance of another model?

I understand from articles like this one that synthetic data generated by one model based on real data can improve the performance of a second model. Can anyone help me understand the intuition behind ...
0 votes
1 answer
86 views

Machine Learning Methods commonly used when data are scarse

It is well-known that deep neural networks require lots of data to perform reliably and well. A commonly-cited statistic is that you need at least 10,000 examples per class for a classification ...
-1 votes
1 answer
43 views

Generating synthetic time series data with limited data

I would like some opinions on my current situation. I have a set of time series data that I want to forecast. The data however is not very long (around 500 rows) so I was looking into generating many ...
0 votes
1 answer
52 views

To train a mushroom vs. non-mushroom image classifier, which images should comprise the negative class?

I want to train a model that will identify if the image is mushroom and non-mushroom. If the image is mushroom, I will use another existing model to categorize if its poisonous or edible. I want to ...
1 vote
3 answers
441 views

Why does MNIST provide only a training and a test set and not a validation set as well?

I was taught that, usually, a dataset has to be divided into three parts: Training set - for learning purposes Validation set - for picking the model which minimize the loss on this set Test test - ...
  • 137
2 votes
1 answer
162 views

Is there an image classification dataset where the class depends on spatial relations?

My question is pretty much the one asked above. To clarify a bit further: I have only found datasets that do object localization and that also have relations between the objects annotated (like: "...
1 vote
0 answers
15 views

Can I use a dataset with real-world images and corresponding actions that the expert took to train an IRL algorithm?

Offline Reinforcement Learning approaches like Inverse Reinforcement Learning/ Batch RL/ imitation learning/ behavior cloning allow us to use previous demonstrations by an expert to learn a policy. ...
1 vote
2 answers
339 views

Does more data increase training accuracy in neural networks?

I was wondering what is the performance benefit of feeding more data to a machine learning model like a neural network? Like I know one of the benefits is that it increases generalization - testing ...
1 vote
1 answer
156 views

Feature Engineering on transactional dataset clustering

I have a data set with transactions details from different business (roughly 1 thousand business entities). Each row is a transaction. The structure of the dataset is as follows: client_id Sex Age ...
1 vote
2 answers
38 views

Master theorem about polynomial classifiers?

Does anyone know if there is a theorem or counterexample establishing whether or not for any given binary classification task in some finite (possibly large) dimensional vector space of attributes, ...
0 votes
0 answers
23 views

How to identify pulse pattern in data

So I am using a pulse sensor which is giving out a certain data. When I place my finger on the sensor and see the data plotted in a graph it shows a varying (non-repetitive as no two pulses are ...
  • 1
0 votes
1 answer
63 views

Meaning of Large Dataset for machine learning

Some online answers about parameters in machine learning mention that it is dependent on the size of dataset we have (if it is a large dataset or not). Is this size related to the number of samples we ...
0 votes
1 answer
165 views

combine two features in dataset?

I have a data set containing the number of security gaps and the level of that gap for a specific website. Now suppose I have 2 features in this data set, the first feature is the number of a ...
1 vote
1 answer
81 views

Datasets input at model.fit produce unexpected results of training loss vs validation loss

Im trying to train a neural network (VAE) using tensorflow and Im getting different results based on the type of input in the model.fit. When I input arrays I get normal difference between the ...
user avatar
0 votes
1 answer
58 views

Should I include overlapping (input) Data in my training data

If I have time dependent data and want to predict the relative change for a future time. Should I separate the data so that the input times don't overlap? With an example: I have hourly temperature ...
0 votes
1 answer
45 views

What should be taken as random variables in the distributions of datasets?

Consider the following two paragraphs taken from the paper titles Generative Adversarial Nets by Ian J. Goodfellow et.al #1: Abstract We propose a new framework for estimating generative models via ...
  • 3,501
1 vote
2 answers
96 views

What makes a 'good' dataset

for the usage of ML technologies, having a appropriate dataset is arguably the first and fundamental step one has to tackle by either aquiring a dataset from external sources or creating their own. ...
  • 11
0 votes
1 answer
61 views

Is there a way to improve the low-quality data?

I'm on a robotics team and we've been tasked to write a program to differentiate between a live and dead fish. We've been given ~15 minutes of training footage and it's absolutely terrible. It's low ...
  • 15
0 votes
0 answers
29 views

Is there any framework for generation of synthetic data where we can set how hard data is to classify?

I am comparing two different training methods of deep neural networks and I was wondering are there any frameworks that can generate x, y datasets but with some input parameter or parameters that can ...
  • 1,240
7 votes
2 answers
770 views

Is there an argument against using the (reviewed) predictions of a model as ground truth to further train exactly this model?

I plan to use my predictions as ground truth to continue training my model. These predictions are of course reviewed during this process. Is there an argument against that (reinforcement of slight ...
  • 73
0 votes
0 answers
19 views

Which existing model could be used for wind speed and direction prediction?

I am trying to predict the wind speed and wind direction in a graph network for a geographical area. The dataset includes the start and end nodes, the distance between them, and wind speed and ...
  • 1
4 votes
1 answer
172 views

What is the total number of actions and rewards count

Reading this two articles about Reinforcement Learning: Deep Reinforcement Learning with Double Q-learning by Hado van Hasselt et al. Human-level control through deep reinforcement learning by ...
  • 143
0 votes
0 answers
33 views

How to use oxford5k for training?

Generally, we have training data with landmark IDs, their GTs (positive samples), and then separate query images and corresponding positive samples for evaluation. In the Oxford5k or ROxford5k, one ...
  • 101
0 votes
3 answers
131 views

How to deal with an unbalanced dataset?

I'm constructing a feed forward neural network that predicts whether a patient will get a stroke or not. However, my dataset is very unbalanced. Out of 5111 rows, 250 contain patients that have had a ...
0 votes
1 answer
46 views

How to create a dataset for binary classification

I would like to classify whether a pot of water is boiling or not using a CNN. Is it enough to take pictures of boiling water using only one pot, or should I use different pots for this to generalize ...
0 votes
1 answer
73 views

Having the negative cases in the same batch vs. shuffling the dataset

I am working on a model for an NLP task. The model encodes the text and has a regression output layer. In this task, from each instance (positive), I create several negative cases using a specific ...
  • 123
0 votes
1 answer
74 views

Is there a standard term for the following flaw in the data?

I wonder if following characteristic of data has some standard "professional" or scientific term associated with it. Let's assume that I have a set of dog/cat images labeled 0 for a cat and ...
  • 1,240
0 votes
0 answers
28 views

What are the "per image" annotations that are generally used for image datasets in AI?

Computer vision is highly benefited by AI algorithms. Image data is abundantly available. There are different varieties of tasks such as image classification, prediction, segmentation, generation, ...
  • 3,501
0 votes
0 answers
36 views

What is all necessary types of data for a bidirectional RNN to learn embeddings?

Bidirectional RNNs are used for generating the semantic vectors of the text at the sentence level and word level. In order to train a CNN for the classification tasks, images, and labels/outputs are ...
  • 3,501
1 vote
0 answers
21 views

What are the types of data in which the order of instances does matter?

In general, the order of instances in the datasets that are used in machine learning is immaterial. But there are exceptions. Timeseries data is one such exception I know. Consider the following two ...
  • 3,501
0 votes
0 answers
12 views

What to predict in a limited transaction dataset?

I have been given a task with a real transaction dataset. The task is to predict something using either logistic regression or simple binary classification. The columns are as follow: Transaction ID ...
2 votes
0 answers
69 views

Does the Frechet Inception Distance (FID) consider color?

I was wondering if the Frechet inception distance for two colored datasets would be the same than the FID calculated for the same datasets converted to grayscale. I know that it depends on the feature ...
  • 221
1 vote
1 answer
79 views

Is there any simple example for volumetric data except from physics and medicine?

Recently I heard about the term volumetric data. The definition for volumetric data is as follows #1: Definition Volumetric data is typically a set S of samples $(x, y, z, v)$, representing the value ...
  • 3,501
2 votes
0 answers
19 views

Do any practical deep learning algorithms deal with tensors containing non-real entries?

In deep learning, most of the applications are from text and images. Both text and images can be converted into a tensor of real numbers. Other than both mentioned above, there may be some other real-...
  • 3,501
0 votes
1 answer
51 views

Generating a dataset from data with "assumed" lables

I've got a task similar to the following: Out of x amount of people, I need to predict, who could be a good athlete and who not. The thing is, I don't have data on the athletic performance of those ...
  • 103
1 vote
1 answer
146 views

Can I use the transformers for the prediction of historical data?

Can I use the transformers for the prediction of wind power with the historical data? Dataset Datetime, Ambient temperature (Degree), Dewpoint (Degree), Relative Humidity\n (%), Air Pressure, Wind ...
3 votes
1 answer
239 views

How to determine the quality of synthetic data?

I'm working on a VAE model to produce synthetic data of X-Ray diffraction spectrums. I try to figure out how I can measure the quality of the spectrums. The goal would be to produce synthetic data ...
  • 33
1 vote
0 answers
31 views

Recommended way to spilt image sequence for training/validation/testing

For object detection tasks I have a few minutes of video footage from a surveillance camera, converted to a sequence of images and ground truth bounding boxes for all people walking by. Now what's the ...
  • 33

1
2 3 4 5 6