# Introduction This lab will guide you through the process of using the Scikit-learn MLPClassifier to compare the performance of different stochastic learning strategies, including SGD and Adam. The MLPClassifier is a neural network classifier that uses backpropagation to optimize the weights of the network. The goal of this lab is to show how different stochastic learning strategies can affect the training loss curves of the MLPClassifier. We will use several small datasets for this example, although the general trend shown in these examples seems to carry over to larger datasets. ## VM Tips After the VM startup is done, click the top left corner to switch to the **Notebook** tab to access Jupyter Notebook for practice. Sometimes, you may need to wait a few seconds for Jupyter Notebook to finish loading. The validation of operations cannot be automated because of limitations in Jupyter Notebook. If you face issues during learning, feel free to ask Labby. Provide feedback after the session, and we will promptly resolve the problem for you.
Click the virtual machine below to start practicing