Dr N. Ahmad (Nasir)

Nasir is an assistant professor in the AI department. His background covers the development of training and simulation techniques for (spiking) neural networks. Currently he is taking inspiration from these models to attempt the development of better machine learning approaches and algorithms. In particular, thinking about how learning speed can be increased by relying on more than just first-order optimization, how distributed and federated learning can be enabled by inspiration from biological systems, how to encode information in spike timing or frequency, and more. Beyond this, he is interested in functional/computational benefits that emerge in systems which are constrained as biology is (e.g. in energy, physical resources etc).

• Natural Computing & Neurotechnology

• Artificial cognitive systems