Advanced Network Security and Cryptography CO3113/CO7113
- Subject Code :
CO3113-CO7113
CO3113/CO7113Assignment1
Thiscourseworkcontributes10%towardsyourCO3113marks.Allrequirementsarecompulsoryand must be implemented.
PlagiarismandCollusion
Plagiarismand/orcollusionwillresultinpenaltiesthatmightgobeyondthisassignment:https://www2.le.ac.uk/offices/sas2/assessments/plagiarism/penalties.
LateSubmissionandMitigatingCircumstance
Latesubmissionpenaltieswillbeapplied.Readthesectionsonlatecourseworksubmissioninyour student handbook or here:https://www2.le.ac.uk/offices/sas2/assessments/late-submission.
Acceptedmitigatingcircumstancesaretheonlywaytowaivelatesubmissionpenalties:https://www2.le.ac.uk/offices/sas2/regulations/mitigating-circumstances.
SubmissionInstructions
SubmityoursolutiononBlackboardbyThursdaythe14thofFebruary,17:00UKtime.Submissions will not be accepted by any other means (e.g., via email).
- You mustsubmitasingleipynbThefilenamemustbeyourusernames(i.e.,ka388).
- You may try it as many times as you like before theOnly the last submission attempt will be marked.
- Code mustexecutewithoutmodifications.YourprojectmustexecuteIfnot, you will lose 20% of the marks assigned to this part of the coursework.
- You must write your The submitted code from any existing sources will be treated as plagiarism and receives 0 marks.
AIPolicy
RedlightfortheGenerativeAItools,whichmeansGenerativeAItools,suchasChatGPT,shallnotbe used. This is an assessment of the independent critical thinking and core theoretical understanding, which includes the core theory and programming skill assessment. Therefore, the students must demonstrate the core knowledge and independent understanding without the aid of AI.
TaskandMarkingScheme
This assignment requires to build a Convolutional Neural Network (CNN) with a usable dataloader, properstructuredesign,andoutputwith theexpectedsize.Anyunsuccessfulimplementationofthe requirements will obtain no marks for that part.
|
Part |
Requirements |
|
1.DataloaderofMNISTdataset. |
Withappropriatedatanormalization.(10%) Databatchescanbedirectlyfedintothe CNN. (10%) |
|
2.ConvolutionalNeuralNetwork |
First convolutional layer with a 5x5 kernel, 16 output channels, a padding of 1, followedbyamaxpoolingoperation.(10%) Second convolutional layer with a 3x3 kernel,32outputchannels,0 padding, followedbyameanpoolingoperation. (10%) Thirdconvolutionallayerwitha1x1kernel, 64 output channels, 0 padding, dropout with0.3,andasigmoidactivationfunction. (10%) Firstfullyconnectedlayerwith120output channels, and a RELU activation function. (10%) Second fully connected layer with 60 outputchannels,andaRELUactivation function. (10%) Thirdfullyconnectedlayerwith10output channels. (10%) |
|
3.Output |
After feeding the data into your CNN model, there is no error and the network produces an output with 10 dimensions.Youmustprint outtheoutputsizeinyour submissionbyusingtheprint()functionin python.(20%) |
