Answered step by step
Verified Expert Solution
Question
1 Approved Answer
Please help with this deep learning!! Code in phyton Note: All problems below are in the context of the MNIST data set, so you must
Please help with this deep learning!! Code in phyton
Note: All problems below are in the context of the MNIST data set, so you must load that as your testing and training set for all your models.
Breadth vs Depth
The most fundamental question when it comes to neural networks is 'how many nodes and how many layers'. I want to try to address the tradeoff in this section. Here, we'll be building networks to classify the MNIST data set, and look at the tradeoff in network shapes.
Problem : A network to classify the MNIST data set will have input nodes, and output nodes one for each of the ten classes How many parameters would a linear softmax model with no hidden layers have? If a model had hidden layers, and nodes in each hidden layer, how many parameters would it have? Call this function Params
Note: I am looking for a mathematical function here in terms of and not a coded solution.
Problem : For a given number of parameters what is the smallest and largest values of such that Params Call this maxk value
Note: What should you do when is not an integer?
One difficulty in comparing network shapes is making the comparison fair. We can say that a comparison between a network of layers and nodes per layer, and a network of layers is 'fair', if both networks have the same or approximately the same total number of parameters.
Step by Step Solution
There are 3 Steps involved in it
Step: 1
Get Instant Access to Expert-Tailored Solutions
See step-by-step solutions with expert insights and AI powered tools for academic success
Step: 2
Step: 3
Ace Your Homework with AI
Get the answers you need in no time with our AI-driven, step-by-step assistance
Get Started