# MLP Regressor

The MultiLayer Perceptron Regressor is a class of feed-forward  artificial neural network. 

There are 4 sorts of  **activation function** to choose from the dropdown list:

* **identity** 
* **logistic**
* **tanh**
* **relu :** Rectified Linear Unit (**ReLU)**

As  a solver, we can implement one of these:

* **lbfgs :** [Broyden–Fletcher–Goldfarb–Shanno algorithm](https://en.wikipedia.org/wiki/Broyden%E2%80%93Fletcher%E2%80%93Goldfarb%E2%80%93Shanno_algorithm)
* **sgd :** [Stochastic gradient descent ](https://en.wikipedia.org/wiki/Stochastic_gradient_descent)
* **adam :** [adam algorithm](https://scikitlearn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html) **in sci-kit learn** 

![](https://1833277725-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-Lyc1OXsKqB2S62LxsOR%2F-M163BllaIFoccNXxg-l%2F-M168BrplgSDnczyRrZi%2Fimage.png?alt=media\&token=ff99d192-96ca-4885-b741-7162d13b5ad6)

![](https://1833277725-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-Lyc1OXsKqB2S62LxsOR%2F-M163BllaIFoccNXxg-l%2F-M167tTLzyeyTJsEYeX-%2FSmartPredict-%20MLP.gif?alt=media\&token=204c69ed-23c9-46e2-8eb3-fa46bd782031)

{% hint style="info" %}
To learn more about the MLP , visit its Sci-kit learn [documentation](https://scikit-learn.org/stable/modules/neural_networks_supervised.html) and [Wikipedia](https://en.wikipedia.org/wiki/Multilayer_perceptron) article.
{% endhint %}