What are the important terminologies related to PyBrain

Recipe Objective - What are the important terminologies related to PyBrain?

There are important terms to keep in mind when working with Pybrain for machine learning. They are as follows: 
* Trained Data: This is the data used to train the Pybrain network.
* Test Data: This is the data used to test the trained Pybrain network.
* Trainer: If we create a network, i. H. a neural network, it trains based on the training data. Whether or not the network is trained now depends on predicting the test data tested on that network. The most crucial concept in Pybrain Training is the use of BackpropTrainer and TrainUntilConvergence.
* Layers: Layers are a set of functions used on the hidden layers of a network.

Learn to Build a Multi Class Image Classification Model in Python from Scratch  
* Connections: A connection works similar to a layer; the only difference is that data moves from node to node on a network.
* Total error: Refers to the error that appears after training the network. If the error changes with each iteration, it still needs time to settle before it shows a constant error between iterations. Once it shows constant error counts, it means the network has converged and remains the same regardless of whether additional training is applied.
* Supervised learning: In this case, we have an input and an output, and we can use an algorithm to map the input to the output. The algorithm learns with the given and iterated training data, and the iteration process stops when the algorithm predicts the correct data.
* Unsupervised: In this case, we have input, but we don't know the output. The role of unsupervised learning is to train yourself as much as possible with the data provided.
* BackpropTrainer: is a trainer that trains the parameters of a module according to a monitored record or ClassificationDataSet (possibly sequentially), propagating errors backward (over time).
* TrainUntilConvergence: Used to train the module on the dataset until it converges.
* modules: modules are networks consisting of input and output buffers.

For more related projects -

https://www.projectpro.io/projects/data-science-projects/deep-learning-projects
https://www.projectpro.io/projects/data-science-projects/keras-deep-learning-projects