The Brain-Like Artificial Intelligence (BLAI) is pioneered by Prof.Nikola Kasabov and here it is one of its realisations.
NeuCube is the world-first development environment and a computational architecture for the creation of Brain-Like Artificial Intelligence (BLAI), that includes applications across domain areas. It is based on the latest neural network models, called spiking neural networks (SNN).
A software implementation of NeuCube is available in the following languages: MATLAB; JAVA; Python (PyNN); C++.
NeuCube software is available for the following computer platforms: PCs; SpiNNaker; GPUs; Cloud based platforms.
NeuCube is a generic system that needs to be tailored for particular applications,using the following steps:
(a) Input data transformation into spike sequences;
(b) Mapping input variables into spiking neurons
(c ) Deep unsupervised learning spatio-temporal spike sequences in a scalable 3D SNN reservoir;
(d) On-going learning and classification of data over time;
(d) Dynamic parameter optimisation;
(e) Evaluating the time for predictive modelling
(f) Adaptation on new data, possibly in an on-line/ real time mode;
(g) Model visualisation and interpretation for a better understanding of the data and the processes that generated it.
(h) Implementation of a SNN model: von Neumann vs neuromorphic hardware systems
A NeuCube architecture for spatio-temporal brain data (STBD) modelling is presented below (paper can be downloaded here):
PUBLICATIONS, PATENTS AND BENCHMARKING
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.
The NeuCube development system in its different software and platform implementations is available subject to licensing agreement.