16
votes
How can I encode angle data to train neural networks?
The main problem with simply using the values $\alpha \in [0, 2\pi]$ is that semantically $0 = 2\pi$, but numerically $0$ and $2\pi$ are maximally far apart. A common way to encode this is by a vector ...
- 1,157
15
votes
Accepted
How can I deal with images of variable dimensions when doing image segmentation?
There are 2 problems you might face.
Your neural net (in this case convolutional neural net) cannot physically accept images of different resolutions. This is usually the case if one has fully-...
- 404
8
votes
Accepted
Is it okay to use publicly available Instagram videos to train an AI?
Under US copyright law, this is probably fair use
...but beware of memorization. You may run into more trouble if the AI outputs things very similar to the original work.
Also, consult a lawyer to ...
- 196
7
votes
Accepted
How many neurons would a network have after a training of 100k small images?
The neural network is typically a set size once it's created. You'd have to create a network big enough for your data-set.
- 368
6
votes
How to generate labels for self-supervised training?
How can I generate the target label from the other data in the dataset?
If you are asking how you can create the learning signal in SSL, when given an unlabelled dataset, for learning representations ...
- 36.3k
5
votes
How to detect LEGO bricks by using a deep learning approach?
So I am assuming that you are trying to detect a lego brick from the image. One idea is that you can use transfer learning. Leveraging a pre-trained machine learning model is called transfer learning. ...
5
votes
Accepted
Small size datasets for object detection, segmentation and localization
There are various dataset available such as
Pascal VOC dataset: You can perform all your task with these.
size of the dataset is as follows
ADE20K Semantic Segmentation Dataset: you can perform ...
- 338
5
votes
Accepted
Why do we need both the validation set and test set?
The difference between the validation and test set in my opinion should be explained in this way:
the validation set is meant to be used multiple times.
the test set is meant to be used only once.
...
- 4,693
5
votes
Accepted
What are "proxy data sets" in machine learning?
In computer science, if you say "A is a proxy for B", then it means that "A replaces B" (temporarily or not), or that "A is used as an intermediary for B".
The term "...
- 36.3k
5
votes
Accepted
Should we also shuffle the test dataset when training with SGD?
Short answer
Shuffling affects learning (i.e. the updates of the parameters of the model), but, during testing or validation, you are not learning. So, it should not make any difference whether you ...
- 36.3k
5
votes
Accepted
Is there an argument against using the (reviewed) predictions of a model as ground truth to further train exactly this model?
Using the (unchecked) predictions of the model as training data is an approach known as "pseudo-labeling". It can help in certain situations, depending on the underlying structure of your ...
- 278
4
votes
What are some datasets to train an MLP on simple tasks?
There are a ton of sample datasets our there you can play with. A bunch of good ones install with R in the datasets package. Luckily you can download them independently if you're not an R user. Try ...
- 3,697
4
votes
Can recommendation systems be created for other data other than images?
Recommendation systems can be applied for anything, as long as you have sufficient training data.
The most important inputs to the recommendation system are not "audio files or video files".
...
- 1,411
4
votes
How can I train a neural network for image classification when the dataset is small?
Use Fine Tuning
You can simply use a pre-trained model on ImageNet, as this data set has multiple snakes classes.
Then you can fine tune the model with your own small data set and outputs.
See this ...
- 515
4
votes
Accepted
What happens to the training data after your machine learning model has been trained?
In many cases, a production-ready model has everything it needs to make predictions without retaining training data. For example: a linear model might only need the coefficients, a decision tree just ...
- 291
4
votes
How could decision tree learning algorithms cope with imbalanced classes?
Decision Tree learners, on their own, are not a good way to deal with imbalanced data. The most commonly used algorithms, by default, make no attempt to address this problem.
If you look carefully at ...
- 9,017
4
votes
What is the reason for taking tuples as vectors rather than points?
They are equivalent. When we consider a particular instance as a vector, we are not literally imagining it as an arrow with it's head at the point coordinates and tail at the origin. It's just when ...
- 249
4
votes
Accepted
How should I generate datasets for a SARSA agent when the environment is not simple?
I am wondering how to generate datasets when the environment is not as simple as a tic-tac-toe or a maze problem
There is no difference in concept, which is why tic-tac-toe and maze problems are used ...
- 25.4k
4
votes
Accepted
Would it be possible to determine the dataset a neural network was trained on?
You can already do this with some neural networks, such as GANs and VAEs, which are generative models that learn a probability distribution over the inputs, so they learn how to produce e.g. images ...
- 36.3k
4
votes
Is there an argument against using the (reviewed) predictions of a model as ground truth to further train exactly this model?
The answer is: It depends.
What you describe is a strategy often used to save time and costs for labelling data. It is important that the data you have already labelled (the 20%) is representative of ...
- 205
4
votes
Accepted
Why does MNIST provide only a training and a test set and not a validation set as well?
The test set should never be seen and ran once at the end of training.
The validation set is used to help you select hyperparameters and it would be cheating to tune your model on the test set because ...
- 56
3
votes
What are some concrete steps to deal with the vanishing gradient problem?
There is not single answer to the vanishing gradient problem. However, there a few things that can help.
As mentioned in the comments, use of Rectified Linear Units (ReLU) as your activation function ...
- 131
3
votes
Accepted
What is the effect of mislabeled training data?
I think the crucial point here is what you precisely mean by mislabelled. Google's image classifier will likely do a 'pretty good' job of retrieving images with the given subject included, but how ...
3
votes
How to classify language as friendly or aggressive with AI?
I did a little search and couldn't find any database that has ground truth for aggressiveness. This means that you need to build yourself a database. This might be huge undertaking. Take thousands of ...
- 330
3
votes
Accepted
Does the quality of training images affect the accuracy of the neural network?
For most of the current use cases, where NNs are used in conjunction with images, the image quality (resolution, color depth) can be low.
Consider image classification for example. The CNN extracts ...
- 1,684
3
votes
Would this relatively small dataset be enough to train a CNN?
Your data set would be what is called "unbalanced' and this can lead to problems in developing an accurate classifier.
The best thing to do (which you might not be able to do) is to find more ...
- 694
3
votes
Would this relatively small dataset be enough to train a CNN?
It is somewhat risky to discuss data independently with your learning mechanism. There is actually no such thing as good data or a good learner. There is only data that is good WITH a particular ...
- 7,345
3
votes
What are examples of techniques to prevent bias in artificial intelligence systems?
It's important to note that, ultimately, the statistical methods we currently use in ML research are just that: statistical methods. So, when they show some "bad behaviour", it's not because ...
- 1,991
3
votes
How can I train a neural network for image classification when the dataset is small?
Besides using transfer learning described in other answer, you should consider using siamese network.
This type of network is used in cases when one does not posess many examples of objects he wants ...
- 333
Only top scored, non community-wiki answers of a minimum length are eligible