Neuroinformatics, Neural Networks and Neurocomputers for Brain-inspired AI

Recorded at IJCNN 2023, 18-23 June, Gold Coast, Queensland, Australia. IJCNN 2023 was sponsored by the International Neural Network Society.

Speaker: Nikola Kasabov, Auckland University of Technology

Abstract: The talk discusses briefly current challenges in AI, including: efficient learning of data (interactive, adaptive, life-long; transfer); interpretability and explainability; personalised predictive modelling and profiling; multiple modality of data (e.g. genetic, clinical, behaviour, cognitive, static, temporal, longitudinal); computational complexity; energy consumption; human-machine interaction.

Opportunities to address these challenges are presented through advancement in Neuroinformatics, Neural networks and Neurocomputers (the 3N). Neuroinformatics offer a tremendous amount of data and knowledge about how the human brain and the nervous system work. Many brain information processing principles can be now implemented in novel Neural network computational models, such as: sparseness of computation, leading to a much less computational complexity and a significant energy consumption; diversity in the NN architecture in terms of type of neurons and compartmentalisation of computations, which can improve results; cognitive computation, where bottom-up sensory information and top-down prior knowledge are used to speeds-up the learning process; life-long and transfer learning; interactive and reinforcement learning (rather than batchmode); self-organisation (rather than pre-defined number of layers and neurons); evolving spatiotemporal knowledge and many more. Some of these principles have already been used in neural network models, such as SOM (Kohonen), ART (Grossberg), ECOS ([1,2]), spiking neural networks (SNN) (Maass), [3]. The latter ones have inspired the development of neuromorphic hardware chips and Neurocomputers, characterised by much low power consumption, massive parallelism and fast processing.

--

You are invited to join INNS and become a member of the premier international society on neural networks: https://www.inns.org/membership-appli...

Learn more about INNS and upcoming conferences at www.inns.org

--
Videography by Ocean Images Production: https://www.oceanimages.com.au/