Teaching Engagements

Course organizer: Prof. Shihua Zhou

Course presenter: Prof Nikola Kasabov; Assistant: Doct. Iman AbouHassan.  

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

Course Content

1. Introduction to the course (Lecture 6.1)

Part I: Learning systems

2. Deep learning and deep knowledge representation in the human brain (Lecture 6.2)

Chapter 3 from: N.Kasabov, ”Time-space, spiking neural networks and brain-inspired artificial intelligence," Springe-Nature, 2019 (Chapter Summary 6.2)

3. Modelling brain dynamics (Lecture 6.3)

• Benuskova, L., Kasabov, N . ”Modeling brain dynamics using computational neurogenetic approach." Cogn Neurodyn 2, 319–334 (2008). https://doi.org/10.1007/s11571-008-9061-1 (Paper 6.3)

4. Evolving learning systems (Lecture 6.4)

• N. Kasabov, ”Evolving fuzzy neural networks for supervised/unsupervised online knowledge-based learning," in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 31, no. 6, pp. 902-918, Dec. 2001, doi: 10.1109/3477.969494. (Paper 6.4)

5. Neuro-fuzzy learning and inference systems: DENFIS (Lecture 6.5)(Chapter Summary 6.5)

• Kasabov, N. K., & Song, Q. (2002).”DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction.” IEEE transactions on Fuzzy Systems, 10(2), 144-154. (Paper 6.5)

6. Spatio-temporal learning systems: SNN (Lecture 6.6)

• N. Kasabov, K. Dhoble, N. Nuntalid, G. Indiveri,”Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. Neural Networks," 41(1995), 188–201 (2013). https://doi.org/10.1016/j.neunet.2012.11.014 .(Paper 6.6)

7. Reservoir computing and Brain-inspired SNN (Lecture 6.7)

• S. Schliebs, A. Mohemmed, N. Kasabov, ”Are probabilistic spiking neural networks suitable for reservoir computing? in International Joint Conference on Neural Networks" (USA, 2011), pp.3156–3163.(Paper- 6.7-1)

• N. Kasabov, ”NeuCube: a spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data .” Neural Netw. 52(2014), 62–76 (2014).(Paper- 6.7-2)

8. Integrated learning systems:

• P. Koprinkova-Hristova, D. Penkov, S. Nedelcheva, S. Yordanov and N. Kasabov, ”On-line Learning, Classification and Interpretation of Brain Signals using 3D SNN and ESN," 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia, 2023, pp. 1-6, https://doi.org/10.1109/IJCNN54540.2023.10191974,(Paper- 6.8-2)

• AbouHassan I., Kasabov N. (2024). ”NeuDen: A Framework for the Integration of Neuromorphic Evolving Spiking Neural Networks with Dynamic Evolving Neuro-Fuzzy Systems for Predictive and Explainable Modelling of Streaming Data," TechRxiv. Preprint.(Paper- 6.8-1)

Part II. Associative memories

9. Spatio-Temporal Associative Memories in SNN (Lecture 6.9)

• Kasabov, Nikola (2023). ”STAM-SNN: Spatio-Temporal Associative Memories in Brain-inspired Spiking Neural Networks: Concepts and Perspectives." TechRxiv. Preprint. https://doi.org/10.36227/techrxiv.23723208.v1

10. Associative memories for neuroimaging data: EEG and fMRI (Lecture 6.10)

• N K. Kasabov, H Bahrami, M Doborjeh, A Wang, ”Brain Inspired Spatio-Temporal Associative Memories for Neuroimaging Data: EEG and fMRI,” Bioengineering 2023, MDPI 10(12), 1341. https://doi.org/10.3390/bioengineering10121341,www.mdpi.com/journal/bioengineering. (Paper- 6.10)

11. Audio-visual associative memories (Lecture 6.11)

• N Kasabov, B Sen Bhattacharya, D Patel, N Aggarwal, T Bankar, I AbouHassan, ”Cognitive Audio-Visual Associative Memories using Brain-inspired Spiking Neural Networks with Case Studies on Moving Object Recognition" (subm. IEEE Trans. Cognitive and Developm. Systems, 2023).

12. Predictive associative memories for time series (Lecture 6.12)

• AbouHassan, I; Kasabov, N; Bankar, T; Garg, R; Sen Bhattacharya, B (2023). ”PAMeT-SNN: Predictive Associative Memory for Multiple Time Series based on Spiking Neural Networks with Case Studies in Economics and Finance.” TechRxiv. Preprint. https://doi.org/10.36227/techrxiv.24063975.v1,https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4665533 (Paper 6.12)

Part III. Software and Hardware Implementation of CogSys.

13. Neuromorphic hardware for CogSys implementations (Lecture 6.13)

• J. Behrenbeck, Z. Tayeb, C. Bhiri, C. Richter, O. Rhodes, N. Kasabov, S. Furber, J. Conrad, Classification and Regression of SpatioTemporal EMG Signals using NeuCube Spiking Neural Network and its implementation on SpiNNaker Neuromorphic Hardware. J. Neural Eng. (IOP Press, Article reference: JNE-102499) (2018). http://iopscience.iop.org/journal/1741-2552. (Paper 6.13a) 

• paper for CogSys on Loihi chip (Paper 6.13b)

14. Software implementations of CogSys. (Lecture 6.14)

• NeuCubePy, NEST, PyNN for SpiNNaker, Lava for Loihi

15. Quantum computation (Lecture 6.15)

• Ravi, N. Kasabov et al, (2023). ”From Quantum Computing to Quantum-inspired Computation for Neuromorphic Advancement – A Survey.” TechRxiv. Preprint. https://doi.org/10.36227/techrxiv.24053250.v1(Paper 6.15)

16. Revision of the course (Lecture 6.16a) (Lecture 6.16b)

Course organizer: Prof. Shihua Zhou

Course presenter: Prof Nikola Kasabov; Assistant: Doct. Iman AbouHassan.  

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

Course Content

1. Introduction to the course: What is MDSE and why we need it? (Lecture 7.1) 

2. Methods for MDSE (Lecture 7.2)

• Budhraja et al., "Mosaic LSM: A Liquid State Machine Approach for Multimodal Longitudinal Data Analysis," 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia, 2023, pp. 1-8, doi: 10.1109/IJCNN54540.2023.10191256. (Paper 7.2)

3. MSDE for biomedical engineering (Lecture 7.3)

• Paper 1: M. Doborjeh, N. Kasabov, Z. Doborjeh, R. Enayatollahi, E. Tu, A. H. Gandomi, Personalised modelling with spiking neural networks integrating temporal and static information," Neural Networks, 119 (2019),162-177 (Paper 7.3-1).

• Paper 2: Sengupta, N., McNabb, C. B., Kasabov, N., & Russell, B. R. (2018). Integrating Space, Time, and Orientation in Spiking Neural Networks: A Case Study on Multimodal Brain Data Modelling. IEEE Transactions on Neural Networks and Learning Systems, 29(11). doi:10.1109/TNNLS.2018.2796023 (Paper 7.3-2)

• Paper 3: Li, Jiawei; Liu, Jinyuan; Zhou, Shihua; Zhang, Qiang; Kasabov, Nikola, , "GeSeNet: A General Semantic-guided Network with Couple Mask Ensemble for Medical Image Fusion" , IEEE Transactions on Neural Networks and Learning Systems, DOI: https://doi.org/10.1109/TNNLS.2023.3293274, 21 July 2023 (Paper 7.3-3).

4-MDSE for predictive modelling of multisensory streaming data (Lecture 7.4) (Chapter 19)

• Paper 1: Maciag, Pi; Bembenik, R; Piekarzewicz A, Del Ser L, Javier; L, Lobo, J; N Kasabov;, Effective Air Pollution Prediction by Combining Time Series Decomposition with Stacking and Bagging Ensembles of Evolving Spiking Neural Networks, Environmental Modelling and Software, vol.170, on line: 16.10.2023, Dec 2023, 105851, https://doi.org/10.1016/j.envsoft.2023.105851;https://www.sciencedirect.com/science/article/pii/S1364815223002372

• Paper 2: H Liu, G Lu,Y Wang, N Kasabov, Evolving spiking neural network model for PM2.5 hourly concentration prediction based on seasonal differences: A case study on data from Beijing and Shanghai, Aerosol and Air Quality Research, vol.21, Issue 2, Feb. 2021, 200247, https://doi.org/10.4209/aaqr.2020.05.0247

• Paper 3: Laña I, Lobo JL, Capecci E, Del Ser J, Kasabov N, Adaptive long-term traffic state estimation with evolving spiking neural networks, Transportation rc.2019.02.011Research Part C: Emerging Technologies 101:126-144 2019, https://doi.org/10.1016/j.t

5. MDSE for integrated audio-visual information processing (Lecture 7.5) 

• Paper 1: N. Kasabov et al, AVIS: a connectionist-based framework for integrated auditory and visual information processing. Inf. Sci. 133, 137–148 (2000) (Paper 7.5-1) (Paper 7.5-2)

• Paper2: N Kasabov, B Bhattacharya, D Patel, N Aggarwal, T Bankar, I AbouHassan, a Cognitive Audio-Visual Associative Memories using Brain-inspired Spiking Neural Networks with Case Studies on Moving Object Recognition (IEEE Trans. Cognitive and Devel. Systems, 2023).(Paper 7.5-3)

6. MDSE for integrating times series and text data in finance and economics (Ms Iman AbouHassan) (Lecture 7.6) 

• Paper: I AbouHassan, N Kasabov, V Jagtap, P Kulkarni, Spiking neural networks for predictive and explainable modelling of multimodal streaming data on the Case Study of Financial Time Series Data and on-line news, SREP, Springer-Nature, Sci Rep 13, 18367 (2023), https://doi.org/10.1038/s41598-023-42605-0. (Paper 7.6)

7. MDSE for integration of brain data and face image data for emotion recognition (Lecture 7.7)​

8. Revision of the course (Lecture 7.8)

Course organizer: A/Prof. Shihua Zhou

Course presenter: Prof Nikola Kasabov; Assistant: Doct. Iman AbouHassan.  

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

Course Content

1. AI and the evolution of its principles. Evolving processes in Time and Space (Ch1, 3-19)

2. From Data and Information to Knowledge. Fuzzy logic. (Ch1,19-33 + extra reading)

3. Artificial neural networks - fundamentals. (Ch2, 39-48).

4. Deep neural networks (Ch.2, 48-50 + extra reading)

5. Evolving connectionist systems (ECOS) (Ch2, 50-78). NeuCom software (IA)

6. Deep learning and deep knowledge representation in the human brain (Ch3)

7. Spiking neural networks (Ch4). Evolving spiking neural networks (Ch5)

8. Brain-inspired SNN. NeuCube. (Ch.6). NeuCube software (IA)

9. Evolutionary and quantum inspired computation (Ch.7)

10. AI applications in health (Ch.8-11)

11. AI applications for computer vision (Ch.12,13)

12. AI for brain-computer interfaces (BCI) (Ch.14)

13. AI for language modelling. ChatBots (extra reading)

14. AI in bioinformatics and neuroinformatics (Ch15,16, 17,18)

15. AI applications for multisensory environmental data (Ch.19)

16. AI in finance and economics (Ch19)

17. Neuromorphic hardware and neurocomputers (Ch20).

Course organizer: A/Prof. Shihua Zhou

Course presenter: Prof Nikola Kasabov; Assistants: A/Prof Wei Qi Yan and Ms. Iman AbouHassan.  

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

Course Content

1. AI and the evolution of its principles. Evolving processes in Time and Space (Ch.1, p.3-19) (Lecture1)

2. From Data and Information to Knowledge. Fuzzy logic. (Ch.1, p.19-33 + Time-Space&AI) (Lecture2)

3. Artificial neural networks - fundamentals. (Ch.2, p.39-48​). Computational modeling with NN (Lecture3) (Tut1: NeuCom)

4. Deep neural networks (Ch.2, p.48-50 + extra reading) (Lecture4) 

5. Evolving connectionist systems (ECOS) (Ch.2, p.52-78). NeuCom software (IA) (Lecture5)(Tutorial2:ECOS in NeuCom)

6. Deep learning and deep knowledge representation in the human brain (Ch.3) (Lecture6)

7. Spiking neural networks (Ch.4). Evolving spiking neural networks (Ch.5) (Lecture7)

8. Brain-inspired SNN. NeuCube. (Ch.6). NeuCube software (IA) (Lecture8 - Tutorial3: NeuCube Software)

9. From von Neuman Machines to Neuromorphic Platforms (Ch.20, p.22) + v.Neumann-AtanasNeuromorphic(Lecture9)

10. Other neurocomputers: Transformers+ Transformers paper(Lecture10)

11. Evolutionary and quantum-inspired computation (Ch.7) (Lecture11)

12. AI applications for brain data: EEG, fMRI (Ch.8-11) (Lecture12)

13. Brain-computer interfaces (BCI) (Ch.14) (Lecture13)

14. AI applications for audio-visual information (Ch.12,13). AI for language modeling (Lecture14)

15. AI in bioinformatics and neuroinformatics (Ch.15,16,17,18) (Lecture15)

16. AI in finance and economics (Ch19) (Lecture16)

17. AI applications for multisensory environmental data (Ch19). Revision of the course. (Lecture17)

Seminar organizer: BAS

Lecturer: Prof Nikola Kasabov

1. Bulgarian participation in the world's first NEMO BMI project "Auto-adaptive neuromorphic brain-machine interface", financed by the European Innovation Council.

2. Watch the lecture at: https://www.youtube.com/watch?v=ZOp51P7NBvE

1- Why brain-inspired computation?

• How is knowledge represented in the brain?

• The challenge is to build AI systems that can learn incrementally and possibly in a life-long learning mode and can be interpreted as knowledge discovery at any phase of their learning.

2- BI-SNN architectures. NeuCube.

• What is a BI-SNN architecture?

• The NeuCube Architecture

• Spike encoding methods

• Spiking neuron models for BI-SNN

• Methods for unsupervised learning in SNN: Spike-Time Dependent Plasticity (STDP)

• Methods for supervised learning in SNN: Rank order (RO) learning rule

• Dynamic Evolving SNN (deSNN)

• Deep learning in NeuCube

• Incremental and transfer learning and knowledge evolution in BI-SNN

• Life-long Learning (LLL) in the brain and in NeuCube

• Time-Space Rule (TSR) representation in BI-SNN – “opening the cube”

• Capturing time-space knowledge as information exchange between clusters

• Capturing knowledge representation in a BI-SNN through supervised learning with deSNN

• Extracting Time-Space Rules (TSR) from a trained NeuCube using EEG data for the GAL task

• NeuCube development environment for SNN system design for TSD

• Implementation of SNN models: From von Neumann principles and Atanassov’s ABC Machine to Neuromorphic Hardware

• Quantum (or quantum-inspired) computation

• Quantum-inspired optimization of eSNN

3- Application specific methods and systems

• Deep learning and deep knowledge representation of neuroimaging spatio-temporal brain data

• Understanding human decision-making

• Understanding brain re-wiring due to mindfulness training using EEG

• Brain Machine Interfaces using Brain-Inspired SNN

• NeuCube for BCI with neurofeedback for prosthetic hands

• BI-SNN for neurorehabilitation

• Learning and understanding brain-VR/AR interaction in time-space

• Deep learning and deep knowledge representation of fMRI data

• Personalized Modelling using both fMRI and DTI data

• Deep learning and modelling of audio and visual and multimodal audio-visual data in BI-SNN

• Deep learning of visual information

• BI-SNN for fast object recognition from video streaming data

• Deep learning and knowledge representation of moving objects using DVS and retinotopic mapping in NeuCube

• Personalized predictive modelling of individual risk of stroke

• Using an ensemble of eSNN for Predicting Hourly Air Pollution in London Area from sensory TSD

• Using BI-SNN as universal machines for explainable and life-long learning systems for various spatio/spectro -temporal data

4- Discussions and Future Directions

• Advantages, Problems, and limitations of BI-SNN

• BI-AI through BI-SNN architectures

• Computational Neuro-Genetic Modelling (CNGM)

• Knowledge-based human-machine interaction and symbiosis based on deep learning, knowledge representation and knowledge transfer with BI-SNN architectures

• Understanding how humans synchronize and transfer knowledge between each other through hyper-scanning and using BI-SNN to model it.

Seminar organizer: Prof. Roumen Trifonov

Lecturers: Prof Nikola Kasabov; Ms. Iman AbouHassan

1. Time Space, Spiking Neural Networks, and Brain-Inspired Artificial Intelligence.

2. Time Series Modeling using the BI-SNN-based NeuCube Architecture.

Course organizer: A/Prof. Basabdatta Bhattacharya

Lecturers: Prof Nikola Kasabov; A/Prof Basabdatta Bhattacharya; Ms. Iman AbouHassan  

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

1. Lecture notes.

2. Project 1: Audio-visual information processing with SNN and NeuCube in particular.

3. Project 2: Develop a NeuCube model that is trained to perform regression analysis on time-series data.

Course organizer: A/Prof. Shihua Zhou

Course presenter: Prof Nikola Kasabov; Assistants: A/Prof Wei Qi Yan and Ms. Iman AbouHassan.

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

                    Wei Qi Yan, "Computational methods for deep learning", Springer 2022.

Course Content

1. Artificial neural networks - fundamentals. Evolving connectionist systems (ECOS) (NK, Chapters 1,2)

2. NeuCom software. Incremental and transfer learning in ECOS (IA, NK).

3. Deep neural networks (DNN) (WQY, NK)

4. Deep learning algorithms (WQY, NK)

5. DNN for image and video (WQY, NK)

6. Brain information processing (Chapter 3).

7. Spiking neural networks and evolving SNN (NK, Chapters 4,5)

8. Brain-inspired computational architectures. NeuCube software (NK, IA, Chapter 6).

9. Evolutionary and quantum computation (NK, Chapter 7).

10. Applications of NN and SNN for financial and economic data modeling (IA, NK, Chapter 19).

11. Other applications of NN, DNN, and SNN. Overview of the course  (NK, WQY, IA)

2- Short Course: Deep Learning in Neural Networks and Applications

The Dalian University of Technology, China, Jun 2022

Course organizer: A/Prof. Shihua Zhou

Lecturers: Prof Nikola Kasabov; A/Prof Wei Qi Yan; Ms. Iman AbouHassan

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

                   Wei Qi Yan, "Computational methods for deep learning", Springer 2022.

Course Content

1. Introduction to Neural Networks and Deep Neural Networks (DNN).

2. Algorithms for Deep Learning 1.

3. Algorithms for Deep Learning 2.

4. Algorithms for Deep Learning 3.

5. Reinforcement learning.

6. Incremental Learning (IL) and Transfer Learning (TL).

   1. IL and TL of vector-based data in evolving neuro-fuzzy systems, exemplified by EFuNN & DENFIS in NeuCom.

   2. IL and TL in brain-inspired SNN, exemplified by NeuCube.

Course organizer: A/Prof. Shihua Zhou

Lecturers: Prof Nikola Kasabov; Ms. Iman AbouHassan

Course Content

1. Artificial Neural Networks Fundamentals: NeuCom software.

2. Spiking Neural Networks.

3. Brain-Inspired Computational Architectures: NeuCube software.

4. Evolutionary and Quantum Computation.

5. Overview of applications of SNN for brain and genetic data modeling.

6. Applications of SNN for streaming multisensory predictive data modeling.​

Course organizer: A/Prof. Basabdatta Bhattacharya

Lecturers: Prof Nikola Kasabov; A/Prof Basabdatta Bhattacharya; Ms. Iman AbouHassan  

Reference: N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence Springer, 2019.

1. Reading chapters.

2. Project 1: Predicting DDoS attack.

3. Project 2: Confused student EEG brainwave data.

4. Project 3: Modeling financial data, the impact of the Covid pandemic on India's trade.