Hot answers tagged

7 votes
Accepted

What is the difference between training and testing in reinforcement learning?

What is reinforcement learning? In reinforcement learning (RL), you typically imagine that there's an agent that interacts, in time steps, with an environment by taking actions. On each time step $t$, ...
user avatar
  • 34.4k
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 ...
user avatar
  • 34.4k
5 votes

What is the difference between training and testing in reinforcement learning?

Reinforcement Learning Workflow The general workflow for using and applying reinforcement learning to solve a task is the following. Create the Environment Define the Reward Create the Agent Train ...
user avatar
  • 627
5 votes
Accepted

Why is my test error lower than the training error?

You use dropout during traing to reduce overfitting, but this reduces the training accuracy. The dropout will not be used during testing, therefore the accuracy will be higher. That's normal behavior ...
user avatar
  • 1,644
4 votes

Why is my test error lower than the training error?

I will just add to all the good answers already here. Like I said on my comment earlier, this is not a bad this(provided you have a split your data correctly). Other reasons could be: High ...
user avatar
3 votes
Accepted

How to evaluate an RL algorithm when used in a game?

When you want to compare Reinforcement Learning algorithms, you might want to compare the average rewards they generate and how fast and close they get to the optimal policy. However, in the case of ...
user avatar
  • 365
2 votes
Accepted

How to decide a train-test split?

I don't think there is any rationale behind choosing 80/20 over 75/25 or others. But those are the numbers for rather small datasets. If your dataset is large enough (like hundreds of thousands of ...
user avatar
  • 870
2 votes
Accepted

What is the time complexity for testing a stacked LSTM model?

The time complexity of an algorithm always depends on its implementation (e.g. searching in a red-black tree has a different time complexity than searching in an unbalanced binary search tree). This ...
user avatar
  • 34.4k
2 votes
Accepted

Is the test time the phase when the model's accuracy is calculated with test data set?

If it is not defined otherwise, testing is the phase where the model is passed with new data instances to derive the score of the test set. It should not be confused with validation set. A validation ...
user avatar
  • 889
1 vote

Is it mandatory to multiply every activation of a layer by droupout factor during testing?

There are two types of dropout, depending on whether a scaling correction is applied during: testing - without dropout applied, to decrease logits by a factor $1-p$ to match the expected magnitude ...
user avatar
  • 24.5k
1 vote
Accepted

Why doesn't dropout mislead results during evaluation?

How/why do we achieve the same/similar results though we are skipping a layer altogether Dropout is not a layer, even tough deep learning libraries implement it as a layer module for convenience. Why ...
user avatar
1 vote

How to do testing for an RNN that was trained with teacher forcing only?

I don't think there's any difference between making predictions when you use or not teacher forcing during training. So, let me describe one way of doing that. During testing, as you noticed, you don'...
user avatar
  • 34.4k
1 vote

What is the difference between training and testing in reinforcement learning?

The goal of the reinforcement learning (RL) is to use data obtained via interaction with the environment to solve the underlying Markov Decision Process (MDP). "Solving the MDP" is tantamount to ...
user avatar
1 vote
Accepted

How to test the robustness of an agent in a custom reinforcement learning environment?

This depends on your definition of robust. Robust to what exactly? Testing different random seeds will test the robustness of the algorithm on stochasticity of the environment and the algorithm's ...
user avatar
1 vote

What are the differences in testing between traditional software and artificial intelligence?

Testing machine learning programs is quite different than testing traditional software. The main reason why this is the case is quite simple, if you're familiar with machine learning. ML programs are ...
user avatar
  • 34.4k
1 vote

How to build a test set for a model in industry?

I am not sure whether that solves your problem at hand, but one approach you could look into is k-fold Cross Validation (CV). In this approach, you split your combined train, development, and test ...
user avatar
  • 705
1 vote

How can I be sure that the final model, trained on all data, is correct?

We usually divide the dataset into multiple subsets namely (training, validation and test sets). During training, we validate the model against the validation set. And during testing, we use the test ...
user avatar
1 vote

How can I be sure that the final model, trained on all data, is correct?

The purpose of the test set is to test your model before deploying, otherwise, you would not need the test set in the first place. If you retrain your model by also including the validation and test ...
user avatar
  • 34.4k
1 vote

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

Assuming that you have access to the training data set, you could use an autoencoder network to predict what features f4, f5, f6 'could be' for the test data set. The way to do this is to train the ...
user avatar
  • 141
1 vote

What is the difference between training and testing in reinforcement learning?

If you want, you can do training and testing in RL. Exactly the same usage, training for building up a policy, and testing for evaluation. In supervised learning, if you use test data in training, it ...
user avatar
1 vote

Should I use leave-one-out cross-validation for testing?

Concerning $k$-fold Cross Validation, I like to think of it by considering two extremes you can do: Leave-One-Out Cross-Validation where you leave one sample each time and train your model on the ...
user avatar
1 vote
Accepted

What is the reason behind using a test batch size?

I am not familiar with using batches during network evaluation. Can someone explain what is the reason behind using it and what are advantages and disadvantages? It is usually just for memory use ...
user avatar
  • 24.5k
1 vote

Is it a good idea to train a CNN to detect the hydration value (percentage) in skin images and evaluate it with the MSE?

Your initial idea seems about right. Before creating your own classifier you might want to try transfer learning, using some pretrained network like VGG16 that is incorporated in most of machine ...
user avatar

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