机器学习代写|5000CEM Lab 3 Machine Learning Techniques

本次英国代写是前馈神经网络相关的assignment

LO3 – Explore reasoning and problems solving approach under uncertainty
conditions.

LO8 – Resolve which of the artificial intelligence approaches offer the best
solution to an intelligent application.
In this lab, you will complete the Basic Tasks, and Advanced Task a) and either
Advanced Task b) or Task c).

See the ‘Getting Started with Lab 3’ video on AULA to give you additional
information on completing this lab.

Lab 3 is part of the coursework submission.

Basic Tasks – ML Techniques

Basic Task a)

Calculate the output from the following artificial neuron. The neuron uses
a threshold based activation function, which means that if the weighted sum
of the inputs is greater than or equal to the threshold the output is 1 and if
the weighted sum of inputs is less than the threshold the output is 0. The
threshold for this neuron is 1.6. (2 marks)

Basic Task b)

For each of the two different pairs of inputs {5,20}, {1,60}, calculate the
outputs from the hidden Neurons A and B as well as the overall prediction
output from the MLP neural network. Input A is the amount of exercise in
hours per day and Input B is the grams of fat that a person eats per day. The
output represents whether a person is healthy or not. For the hidden units
and output unit you should apply the sigmoid activation function. (2 marks)

Basic Task c)

Cornelius and Shila are standing for election. It has been decided that by
using a decision tree it is possible to predict people’ voting patterns using
characterises such as income, gender and whether the person as voted
before.

Using entropy and information gain (ID3 Approach) or the Gini
impurity approach determine using the data in the table the decision tree
root attribute. (2 marks)