From the course: Applied AI for IT Operations (AIOps)
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Building a classification model with Keras - Python Tutorial
From the course: Applied AI for IT Operations (AIOps)
Building a classification model with Keras
[Instructor] We now continue on the previous video and create a softmax model with three dense layers in Keras to predict the root cause based on the symptoms. it's highly recommended for the students to have prior understanding of how deep learning and Keras work for learning these examples. First, we set up the hyperparameters for the neural network. We set epochs to 20 and a batch size of hundred. Please note that we have thousand samples in the dataset, so there will be 10 batches overall. We set verbose to be one. So we can view the details of model training. The number of output classes will be set to match the unique number of labels in the target variable, namely root cause. We will then try with a hidden layer size of 128. For validation we split 20% of the thousand input records to be validation data. Now we can create a sequential model. We add the first hidden layer as a dense layer with activation as RLU also called rectified linear unit. We add a second similar layer…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.