From the course: Neural Networks and Convolutional Neural Networks Essential Training
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Understanding the components in Keras
From the course: Neural Networks and Convolutional Neural Networks Essential Training
Understanding the components in Keras
- [Instructor] Keras is a high level neural network's API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. Let's take a look at some of the components of Keras, starting with compile. Before training a model, you need to configure the learning process, which is done via the compile method. It receives three arguments, the optimizer, this is the algorithm that given a set of parameters returns one with a smaller loss function, the loss, this is the objective function for measuring the accuracy of performance error of a neural network, and finally the metrics, which is the list of metrics. For any classification problem, you will want to set this metrics to accuracy. So let's take a look at the first parameter, which is the optimizer. You can either call it by name, using the default parameter values, or you can instantiate an optimizer before passing it to the model or compile function. In our examples, we will first instantiate them by calling them by…
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.
Contents
-
-
-
-
-
Understanding the components in Keras2m 12s
-
Setting up a Microsoft account on Azure1m 57s
-
Introduction to MNIST5m 33s
-
Preprocessing the training data4m 38s
-
Preprocessing the test data1m 58s
-
Building the Keras model2m 23s
-
Compiling the neural network model2m 18s
-
Training the neural network model1m 27s
-
Accuracy and evaluation of the neural network model2m 4s
-
-
-
-
-
-