NeuCube Brain-inspired Neuromorphic Development System for AI

KEDRI at AUT has developed the world first brain-inspired development system for the creation of spiking neural network (SNN) based AI application systems, named NeuCube. It is an open source software written in both Matlab and Python. NeuCube is being using in more than 50 labs across 25 countries for teaching, research and industrial AI applications.  Some AI applications include: predicting mental health events (NZ, Singapore, UK, Australia); wind-turbine power prediction (Italy); financial modelling (Bulgaria, India); prosthetics control (China, France, Bulgaria); affective computing (NZ, Japan); predicting air pollution (Poland; China); predicting earthquakes (NZ, China); building hybrid SNN-quantum computers (UK); machine consciousness (NZ, UK).

The proposed NeuCube framework and computational architecture enable the creation of intelligent systems, that when compared with traditional statistical and machine learning methods, showed superior results in the following aspects: 1) Better data analysis and classification/regression accuracy (by 10 to 40%); 2) Better visualisation of the created models, with a possible use of VR; 3) Better understanding of the data and the processes that are measured; 4) Enabling new information and knowledge discovery through meaningful interpretation of the models.

Description of the NeuCube with selected applications is published in the following papers:

• N.Kasabov, V.Feigin, Z.Hou, Y.Chen, Improved method and system for predicting outcomes based on spatio/spectro-temporal data, PCT patent WO2015/030606 A2, US2016/0210552 A1. Granted/Publication date: 21 July 2016.
• Kasabov, N. NeuCube: A Spiking Neural Network Architecture for Mapping, Learning and Understanding of Spatio-Temporal Brain Data, Neural Networks vol.52 (2014), pp. 62-76, http://dx.doi.org/10.1016/j.neunet.2014.01.006
• Nikola Kasabov, Nathan Matthew Scott, Enmei Tu, Stefan Marks,Neelava Sengupta, Elisa Capecci, Muhaini Othman, Maryam Gholami Doborjeh, Norhanifah Murli, Reggio Hartono, Josafath Israel Espinosa-Ramos, Lei Zhou, Fahad Bashir Alvi, Grace Wang, Denise Taylor, Valery Feigin, Sergei Gulyaev, Mahmoud Mahmoud, Zeng-Guang Hou, Jie Yang (2015) Evolving Spatio-Temporal Data Machines Based on the NeuCube Neuromorphic Framework:Design Methodology and Selected Applications. Neural Networks Journal, Special Issue on Neural Network Learning in Big Data, 2015, Elsevi
• N.Kasabov, From Multilayer Perceptrons and Neuro-Fuzzy Systems to Deep Learning Machines: Which Method to Use? – A Survey, Int. Journal on Information Technologies and Security, vol.9, No. 20, 2017, 3-24.
• N.Sengupta, N. Kasabov, Spike-time encoding as a data compression technique for pattern recognition of temporal data, Information Sciences 406–407 (2017) 133–145.