ENG4200 Neural networks

Coursework 2: Neural networks 

ENG4200 Introduction to Artificial Intelligence and Machine Learning 4 

1. Key Information 

• Worth 30% of overall grade 

• Submission 1 (/2): Report submission 

• Deadline uploaded on Moodle 

• Submission 2 (/2): Code submission to CodeGrade 

• Deadline uploaded on Moodle (the same as for report) 

2. Training data 

The training dataset has been generated by maximum flow analysis between nodes 12 and 2. The 

feature dataset has 19 fields, which of each represents the maximum flow capacity of each of the 

19 edges, taking the values of 0, 1, and 2. The output dataset has 20 fields, where the first 19 

fields refer to the actual flow taking place on each of the 19 edges, and the last one refers to the 

maximum flow possible between nodes 12 and 2. 

Figure 1 The network used to generate training dataset. This information is just to help you understand the training 

dataset; you must not generate additional training dataset to train your neural network. 

 3. What you will do 

You have to create and train a neural network with the following requirement/note: 

• Only the provided training dataset should be used, i.e. furthur traning dataset must NOT be 

created by performing maximum flow analysis over the network in Figure 1. 

• The accuracy on a hidden test dataset will be evaluated by a customised function as 

follows, where the accuracy on the maximum flow field is weighted by 50%, and other 19 

fields share the rest 50% (you may design your loss function accordingly): 

 You should prepare two submissions, code submission and report submission. In blue colour are 

assessment criteria. 

• Code submission should include two files (example code uploaded on Moodle): 

o A .py file with two functions 

▪ demo_train demonstrates the training process for a few epochs. It has three 

inputs: (1) the file name of taining feature data (.csv), (2) the file name of 

training output data (.csv), and (3) the number of epochs. It needs to do two 

things: (1) it needs to print out a graph with two curves of training and 

validation accuracy, respectively; and (2) save the model as .keras file. 

▪ predict_in_df makes predictions on a provided feature data. It has two 

inputs: (1) the file name of a trained NN model (.keras) and (2) the file name 

of the feature data (.csv). It needs to return the predictions by the NN model 

as a dataframe that has the same format as ‘train_Y’. 

o A .keras file of your trained model 

▪ This will be used to test the hidden test dataset on CodeGrade. 

o You can test your files on CodeGrade. There is no limit in the number of 

submissions on CodeGrade until the deadline. 

o Assessment criteria 

▪ 5% for the code running properly addressing all requirements. 

▪ 10% for a third of the highest accuracy, 7% (out of 10%) for a third of the 

second highest accuracy, and 5% (out of 10%) for the rest. 

• Report submission should be at maximum 2 pages on the following three questions and 

one optional question: 

o Parametric studies of hyperparameters (e.g. structure, activators, optimiser, learning 

rate, etc.): how did you test different values, what insights have you obtained, and 

how did you decide the final setting of your model? 

o How did you address overfitting and imbalanced datasets? 

o How did you decide your loss function? 

o [Optional] Any other aspects you’d like to highlight (e.g. using advanced methods 

such as graphical neural network and/or transformer)? 

o [Formatting] Neither cover page nor content list is required. Use a plain word 

document with your name and student ID in the first line. 

o Assessment criteria 

▪ 5% for each of the questions, evaluated by technical quality AND 

writing/presentation 

▪ Any brave attempts of methods (e.g. Graphical Neural Network, Transformer, 

or Physics-Informed Neural Network using physical relationships e.g. that 

the flows going in and out of a node should be balanced) that go beyond 

what we learned in classroom will earn not only the top marks for report, but 

also (unless the accuracy is terribly off) will earn a full 10% mark for 

accuracy in the code submission part. If you have made such attempts, don’t 

forget to highlight your efforts on the report.