From the course: Neural Networks and Convolutional Neural Networks Essential Training
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Neural network visualization
From the course: Neural Networks and Convolutional Neural Networks Essential Training
Neural network visualization
- [Instructor] This is a good opportunity for us to consolidate our understanding before moving on. So let's head over to our browser and type playground.tensorflow.org or alternatively you can just Google for playground, space, tensor flow. You should see a website that looks something like this. And let's make sure that we understand some of the terms here. So we're going to be using the dataset at the bottom left to start off with. We have two features or inputs X1 and X2, and Epoch as a complete past through the dataset. Remember that there were too components to gradient decent, the direction to move in and the size of the step. While the learning rate is the size of the step. And let's move that to 0.3. The activation functions determine what causes the neuron to fire. In this case, the activation function is the hyperbolic tangent or Tanh. The purpose of regularization L1 and L2 is to reduce over fitting. Over fitting is when a model works very well for the data that it was…
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.