Module Specification

The information contained in this module specification was correct at the time of publication but may be subject to change, either during the session because of unforeseen circumstances, or following review of the module at the end of the session. Queries about the module should be directed to the member of staff with responsibility for the module.
Title NEURAL NETWORKS
Code ELEC320
Coordinator Dr AF Garcia-Fernandez
Electrical Engineering and Electronics
Angel.Garcia-Fernandez@liverpool.ac.uk
Year CATS Level Semester CATS Value
Session 2020-21 Level 6 FHEQ Second Semester 7.5

Aims

Understand the basic structures and the learning mechanisms underlying neural networks within the field of artificial intelligence and examine how synaptic adaptation can facilitate learning and how input to output mapping can be performed by neural networks.

Obtain an overview of linear, nonlinear, separable and non separable classification as well as supervised and unsupervised machine learning.


Pre-requisites before taking this module (other modules and/or general educational/academic requirements):

 

Co-requisite modules:

 

Learning Outcomes

(LO1) Learning  the advantages and main characteristics of neural networks in relation to traditional methodologies. Also, familiarity with different neural networks structures and their learning mechanisms.

(LO2) Understanding of the neural network learning processes and their most popular types, as well as  appreciation of how neural networks can be applied to artificial intelligence problems.

(S1) On successful completion of this module the student should be able to pursue further study in artificial intelligence and more advanced types of neural networks.

(S2) On successful completion of this module the student should be able to analyse numerically the mathematical properties of most major network types and apply them to artificial intelligence problems.

(S3) On successful completion of this module the student should be able to approach methodically artificial intelligence problems and understand the principal mathematics of learning systems.


Syllabus

 

Introduction
Chapter 1 Structural Aspects
Chapter 2 Learning Processes
Chapter 3 Single-Layer Perceptron
Chapter 4 Multi-Layer Perceptron
Chapter 5 Radial-basis Function Networks
Chapter 6 Support Vector Machines
Chapter 7 Self-Organising Maps


Teaching and Learning Strategies

Due to Covid-19, one or more of the following delivery methods will be implemented based on the current local conditions and the situation of registered students.

(a) Hybrid delivery, with social distancing on Campus

Teaching Method 1 - On-line asynchronous lectures
Description: Lectures to explain the material
Attendance Recorded: No
Notes: On average one per week

Teaching Method 2 - Synchronous face to face tutorials
Description: Tutorials on the Assignments and Problem Sheets
Attendance Recorded: Yes
Notes: On average one per fortnight

(b) Fully online delivery and assessment

Teaching Method 1 - On-line asynchronous lectures
Description: Lectures to explain the material
Attendance Recorded: No
Notes: On average one per week

Teaching Method 2 - On-line synchronous tutorials
Descrip tion: Tutorials on the Assignments and Problem Sheets
Attendance Recorded: Yes
Notes: On average one per fortnight

(c) Standard on-campus delivery with minimal social distancing

Teaching Method 1 - Lecture
Description: Lectures
Attendance Recorded: Yes

Teaching Method 2 - Tutorial
Description: Tutorials
Attendance Recorded: Yes


Teaching Schedule

  Lectures Seminars Tutorials Lab Practicals Fieldwork Placement Other TOTAL
Study Hours 12

  6

      18
Timetable (if known)              
Private Study 57
TOTAL HOURS 75

Assessment

EXAM Duration Timing
(Semester)
% of
final
mark
Resit/resubmission
opportunity
Penalty for late
submission
Notes
Assessment 1 Standard UoL penalty applies for late submission. Assessment Schedule (When) :Semester 2 examination period  2 hours    70       
CONTINUOUS Duration Timing
(Semester)
% of
final
mark
Resit/resubmission
opportunity
Penalty for late
submission
Notes
Due approximately week 9      30       

Reading List

Reading lists are managed at readinglists.liverpool.ac.uk. Click here to access the reading lists for this module.