- Student Records
Programme & Unit Catalogues

CM50269: Neural computation

Follow this link for further information on academic years Academic Year: 2018/9
Further information on owning departmentsOwning Department/School: Department of Computer Science
Further information on credits Credits: 6      [equivalent to 12 CATS credits]
Further information on notional study hours Notional Study Hours: 120
Further information on unit levels Level: Masters UG & PG (FHEQ level 7)
Further information on teaching periods Period:
Semester 2
Further information on unit assessment Assessment Summary: CW 100%
Further information on unit assessment Assessment Detail:
  • Written Report on Case Study (CW 50%)
  • Completed Lab Report (CW 50%)
Further information on supplementary assessment Supplementary Assessment:
Like-for-like reassessment (where allowed by programme regulations)
Further information on requisites Requisites:
Further information on descriptions Description: Aims:
To convey the detailed theory and practice of a wide range of contemporary and historical neural computation (and related) data modelling approaches.

Learning Outcomes:
After completion of the unit, students should be able to:
* critically appraise the historical development of the field,
* advocate the relevance of neural computation models to problems in data science,
* explain in detail the theory behind key neural computing models,
* implement a neural network model from first principles in a relevant programming language (e.g. Python),
* apply complex neural computing model software (e.g. for "deep learning") in a data science context and critically evaluate the results.

Intellectual skills:
* Conceptual understanding of modelling architectures (T,F,A)
* Critical analysis of algorithms (T,F,A)
Practical skills:
* Implementation of neural computing algorithms (T,F,A)
* Application of deep learning models (T,F,A)
Transferable skills:
* Numerical programming (F,A)
* Optimisation methods (F,A)

Topics covered include the history of the field and development of artificial neural network models, the variety of neural computing paradigms, technical aspects arising in the fitting of models (e.g. nonlinear optimisation), and motivation for and use of contemporary "deep learning" approaches.
Further information on programme availabilityProgramme availability:

CM50269 is Optional on the following programmes:

Department of Computer Science