# Tag Info

## Hot answers tagged testing

5

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 if you work with dropout.

5

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 $t$, the agent takes the action $a_t \in \mathcal{A}$ in the state $s_t \in \mathcal{S}$, receives a reward (or reinforcement) signal $r_t \in \mathbb{R}$ from the ...

4

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 and Validate the Agent Deploy the Policy Training Training in Reinforcement learning employs a system of rewards and penalties to compel the computer to solve ...

3

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 dropout rate or excessive data augmentation could be one of the reason. This can cause the training accuracy to appear low whist in reality the model is in fact ...

3

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 comparing it to humans, you might want to compare the game results of all the games played. Reward Comparison Often Reinforcement Learning algorithms are ...

3

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 shuffle or not the test or validation data (unless you are computing some metric that depends on the order of the samples), given that you will not be computing ...

3

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 samples), you can even work with 98/1/1 percents for train/val/test as discussed by Andrew Ng in this video. Neural networks thrive with big data and it is always ...

2

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 dataset is a sample of data held back from training your model that is used to give an estimate of model skill while tuning model’s hyperparameters during ...

2

Goodness is subjective. Reliable knowledge isn't possible with that flimsy a quality objective. The sturdy objective criteria you gave is 95%, so it is bad by that criteria. (I'm assuming that the 95% is expected for a given data set or a randomized sample from a given data set.) However, the 80% accuracy is good by the criteria where the you sum the ...

1

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 optimization procedure. Trying different hyperparameters would test the robustness of the algorithm to hyperparameter changes. Some RL benchmarks have their own ...

1

I no longer really use validation that much, but rather only training and testing. Why? Because I mostly follow Ron Kohavi's (Stanford Univ) approach to CV. I have done a lot of validation but it seemed to be overkill, essentially causing me to ask why I have this very small-sampled parameter watch on the side from which I am supposed to learn from. You ...

1

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 not just if statements and loops, but they are composed of models, which can even be black-box models, such as neural networks (i.e. it's difficult to interpret ...

1

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 data into $k$ randomized and equally-sized partitions. Afterwards, you train and evaluate your model $k$ times. In the $i^{th}$ iteration, you train your model on ...

1

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 dataset to obtain metrics for the model. We should make sure the subsets are taken from the same sample. Once you've tested it against the test subset, there's ...

1

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 datasets, of course, you cannot test your model anymore. You need to leave the test dataset separate and not use it for retraining, unless you have more data for ...

1

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 autoencoder on the training data set with features f1, f2, f3 as inputs, and then use f1,f2,f3,f4,f5,f6 as the output of the network. The autoencoder then ...

1

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 finding the optimal policy (with respect to the MDP's underlying dynamics which are usually assumed to be stationary). Training is the process of using data in ...

1

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 is like cheating. You cannot trust the evaluation. That's why we separate train and test data. The Objective of RL is a little different. RL trying to find the ...

1

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 remaining $n-1$, and 2-fold Cross Validation at which you split your dataset in half and train (and validate) two models on two different halves. The important ...

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