ELEC 6004 Neuromorphic Electronics Design
Credit Points 10
Description Efficient, parallel, low-power computation is a hallmark of brain computation and the goal of neuromorphic engineering. The focus of this unit is to design, implement and test accurate, electronic, very large scale integrated (VLSI) circuit model of neural systems and the associated signal processing. Students will have opportunities to design and build a neural system on hardware and gain resultant insights into applying neuromorphic engineering to real-world problems.
School Graduate Research School
Student Contribution Band HECS Band 2 10cp
Check your HECS Band contribution amount via the Fees page.
Restrictions Students must be enrolled in 8124 Master of Applied Neuromorphic Engineering
- Design and implement Leaky Integrate-and-Fire (LIF) neuron circuits on Field-Programmable Gate Arrays (FPGAs) using Verilog Hardware Description Language (HDL).
- Develop and implement spiking neural network systems to process event-based data using Verilog/Python
- Develop a solution-orientated way of critically assessing real-world problems architecturally
- Communicate the significance and impact of digital neuromorphic systems to non-specialist audiences
- Knowledge and skills of implementing a High-speed interface between a hardware platform and PCs to realise high speed data transmission between the hardware and PCs
- Skills of designing and implementing a LIF neural network system on a hardware platform and PCs
- Knowledge and skills of architectural design of a neuromorphic system
The following table summarises the standard assessment tasks for this subject. Please note this is a guide only. Assessment tasks are regularly updated, where there is a difference your Learning Guide takes precedence.
|Practical||1200 words or equivalent||30||N||Individual|
|Practical||1200 words or equivalent||25||N||Individual|
|Practical||1500 words or equivalent||30||N||Group|