From the course: Neural Networks and Convolutional Neural Networks Essential Training
Join today to access over 25,300 courses taught by industry experts.
Solution: How many parameters?
From the course: Neural Networks and Convolutional Neural Networks Essential Training
Solution: How many parameters?
In this challenge, we're trying to calculate the total number of weights or parameters for the neural network that we're creating to classify images from the Fashion MNIST dataset. Now we have a total of 100,480 weights for the first section. We have 128 times 64 plus 64 for the next section. So that's a total of 8,256. And we have 64 times 10 plus 10 in the final section. So this is a total of 650 weights. And so if you go ahead and total the number of weights or parameters for each of the different sections, we have a total of 109,386 weights. So now that you know how to calculate the total number of weights, let's take a look at calculating the loss of a neural network.
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.