From the course: Deep Learning: Getting Started
Join today to access over 25,900 courses taught by industry experts.
Building the RCA model
From the course: Deep Learning: Getting Started
Building the RCA model
Now, we define our training configuration and build our neural network in section 7.3. We start by importing Keras, the optimizers module, and the L2 regularizer. Then we set up hyperparameters, epochs is set to 20, we will train longer than the previous examples because this problem might need more iterations to learn well. size is 64, verbose is 1 for detailed output, and validation split is 0.2 to reserve 20% of the training data for validation. We determine output classes by counting the number of unique classes in our label encoder. This ensures that our model output matches our actual number of root causes. Then hidden is set to 128 nodes per hidden layer, giving the model good capacity to learn complex patterns. We create a sequential model and add an input layer with a shape of 7 comma to match the 7 symptom features. Then add two dense hidden layers, each with 128 nodes and ReLU activation. These layers learn to recognize patterns in the symptom combinations that indicate…
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.
