CECS Professional Skills Mapping

COMP4660 — Neural Networks, Deep Learning and Bio-inspired Computing

code: COMP4660
name: Neural Networks, Deep Learning and Bio-inspired Computing
unit value: 6
description: A neural network is a computational paradigm based on insights from the brain, consisting of many simple processing elements together producing complex computations. Deep learning uses many neural network layers for advanced feature recognition and prediction.

Bio-inspired Computing is the combination of computational intelligence and collective intelligence. These computational methods are used to solve complex problems, and modeled after design principles encountered in natural / biological systems, and tend to be adaptive, reactive, and distributed. The goal of bio-inspired computing is to produce computational tools with enhanced robustness, scalability, flexibility and which can interface more effectively with humans.

This course introduces the fundamental topics in bio-inspired computing, and build proficiency in the application of various algorithms in real-world problems. The course will also cover applications focused particularly on highly sophisticated interaction with users.
P&C: https://programsandcourses.anu.edu.au/course/COMP4660
course learning outcomes:
  1. Demonstrate an advanced theoretical understanding and ability to apply models in neural networks
  2. Demonstrate an advanced theoretical understanding and ability to apply models in deep learning
  3. Demonstrate an advanced theoretical understanding and ability to apply models in evolutionary algorithms
  4. Have the knowledge and skills to compare and select the most appropriate method from: neural, deep learning, evolutionary or hybrid method for any application / data set.
  5. Demonstrate an advanced theoretical understanding of the differences between these major bio-inspired computing methods, including the advantages and disadvantages of each
assessment:
  1. Quizzes (25%)
  2. Assignment 1 (15%)
  3. Assignment 2 (15%)
  4. Final Exam (35%)
  5. Peer review (10%)

Mapped learning outcomes

learning outcome1. KNOWLEDGE AND SKILL BASE2. ENGINEERING APPLICATION ABILITY3. PROFESSIONAL AND PERSONAL ATTRIBUTESassessment tasks
1.11.21.31.41.51.62.12.22.32.43.13.23.33.43.53.612345
  1. Demonstrate an advanced theoretical understanding and ability to apply models in neural networks
  1. Demonstrate an advanced theoretical understanding and ability to apply models in deep learning
  1. Demonstrate an advanced theoretical understanding and ability to apply models in evolutionary algorithms
  1. Have the knowledge and skills to compare and select the most appropriate method from: neural, deep learning, evolutionary or hybrid method for any application / data set.
  1. Demonstrate an advanced theoretical understanding of the differences between these major bio-inspired computing methods, including the advantages and disadvantages of each

Course contribution towards the Engineers Australia Stage 1 Competency Standard

This table depicts the relative contribution of this course towards the Engineers Australia Stage 1 Competency Standard. Note that this illustration is indicative only, and may not take into account any recent changes to the course. You are advised to review the official course page on P&C for current information..

1. KNOWLEDGE AND SKILL BASE
1.1
 
1.2
 
1.3
 
1.4
 
1.5
 
1.6
 
2. ENGINEERING APPLICATION ABILITY
2.1
 
2.2
 
2.3
 
2.4
 
3. PROFESSIONAL AND PERSONAL ATTRIBUTES
3.1
3.2
 
3.3
 
3.4
 
3.5
 
3.6
 

Engineers Australia Stage 1 Competency Standard — summary

1. KNOWLEDGE AND SKILL BASE
1.1Comprehensive, theory based understanding of the underpinning natural and physical sciences and the engineering fundamentals applicable to the engineering discipline.
1.2Conceptual understanding of the, mathematics, numerical analysis, statistics, and computer and information sciences which underpin the engineering discipline.
1.3In depth understanding of specialist bodies of knowledge within the engineering discipline.
1.4Discernment of knowledge development and research directions within the engineering discipline.
1.5Knowledge of contextual factors impacting the engineering discipline.
1.6Understanding of the scope, principles, norms, accountabilities and bounds of contemporary engineering practice in the engineering discipline.
2. ENGINEERING APPLICATION ABILITY
2.1Application of established engineering methods to complex engineering problem solving.
2.2Fluent application of engineering techniques, tools and resources.
2.3Application of systematic engineering synthesis and design processes.
2.4Application of systematic approaches to the conduct and management of engineering projects.
3. PROFESSIONAL AND PERSONAL ATTRIBUTES
3.1Ethical conduct and professional accountability.
3.2Effective oral and written communication in professional and lay domains.
3.3Creative, innovative and pro-active demeanour.
3.4Professional use and management of information.
3.5Orderly management of self, and professional conduct.
3.6Effective team membership and team leadership.

Updated:  18 February 2021/ Responsible Officer:  Dean, CECS/ Page Contact:  CECS Academic Education Services