Artificial Neural Network (ANN) Model

ANN models strive to learn relationships through different sets of data. With this information, ANN models can be used to predict outcomes.

In this assignment, students will build an ANN, then write a comprehensive technical report as a Python Jupyter notebook (to include all code, code comments, all outputs, plots, and analysis). Make sure the project documentation contains:

a) Problem statement

b) Algorithm of the solution

c) Analysis of the findings

d) References

Download the “NFL Players Dataset,”

https://www.kaggle.com/datasets/toddsteussie/nfl-play-statistics-dataset-2004-to-present

. The dataset contains football players’ characteristics.

1. Select from a pool of 200 “Active Players” and 200 “Retired Players.”
2. Define “optimal team” based on your decision of the player characteristics necessary to build a team: -Starting offense (11 players): passing, rushing, and receiving. -Starting special teams (11 players): punting, punt returns, and kick returns. -Starting defense (11 players): tackles, sacks, safeties, and fumbles.
3. Your task is to identify the optimal team from each pool comprised of 33 “Active Player” and “Retired Player” members.
4. Examine the multilayer neural network MLP architecture depicted in the “DSC-550 An Artificial Neural Network Model Image.”(attached)

Build a deep artificial neural network MLP to include the following:

a) 1 input layer

b) As many hidden layers as you deem necessary

c) An output layer fully connected to the hidden layers.

1. Explain your architecture and how the NFL player characteristics are used as inputs.

Activate the MLP by performing the following steps:

1. Starting at the input layer, forward propagate the patterns of the training data through the network to generate an output.
2. Based on the network’s output, calculate the error that we want to minimize using a cost function that we will describe later.
3. Back propagate the error, find its derivative with respect to each weight in the network, and update the model.
4. Repeat steps 1 through 3 for multiple epochs and learn the weights of the MLP.
5. Use forward propagation to calculate the network output and apply a threshold function to obtain the predicted class labels in the one-hot representation.

Interpret the output of your MLP in the context of selecting an optimal football team. DSC-550 An Artificial Neural Network Model Image
Directions: Refer to this image when working on the “Artificial Neural Network (ANN)”
assignment.
Figure 1. An Artificial Neural Network Model. Reprinted from Python Machine Learning: Machine
Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2 (3rd ed.), by Raschka, S. and
Mirjalili, V., 2019, p. 388, Packt Publishing.
© 2023. Grand Canyon University. All Rights Reserved.