Thesis Project Form

Biologically inspired model that uses spiking neural networks combined with a “wake” and a “sleep” phase learning phase have been recently proposed ad implemented.

The goal of the thesis is to implement the neural dynamics in real-time onto the DYNAP-SE mixed-signal spiking neural network chip. The neural network chip will be interfaced to a computer in-the-loop that will be used to implement the reinforcement-learning protocol. The goal is to validate the model and verify its robustness to biologically relevant constraints, such as limited precision, low resolution, sensitivity to noise, and in-homogeneity of neuron and synapse circuits.
Accordingly, the main tasks will be the following ones:
• implement an on-chip a recurrent spiking network capable to learn in a supervised fashion the world model;
• build the agent-module that will be interfaced to a computer in-the-loop, which will be used to implement the reinforcement-learning protocol;
• validate the model and verify its robustness to biologically relevant constraints;
• benchmark the architecture on standard discrete control tasks.

The student will learn to employ different methodologies and instrumentation, including:
- Modeling of spiking neural networks using the Python Brian neural network simulator
- Programming scalable multi-core dynamic neuromorphic asynchronous spiking neural network processors (DYNAP-SE)