Ayodele Lasisi

Work place: Faculty of Computer Science & Information Technology, Universiti Tun Hussein Onn Malaysia, 86400 Parit Raja, Batu Pahat, Johore, Malaysia

E-mail: lasisiayodele@yahoo.com


Research Interests: Computer systems and computational processes, Artificial Intelligence, Pattern Recognition, Data Structures and Algorithms


Ayodele Lasisi received his Ph.D from the FSKTM, UTHM. He currently holds a lecturing position as Lecturer I in Computer Science in the Department of Mathematical Sciences under the Faculty of Science at Augustine University, Ilara-Epe, Lagos State, Nigeria. He holds a Masters Degree with distinctions from International Islamic University Malaysia (IIUM) with specialisation in Computer Networking & Linux Administration. He completed his B.Sc. (Hons) Degree in Computer Science from Babcock University, Nigeria. His research interests include Artificial Intelligence, Computer Security, Data Communications and Networking, and Pattern Recognition. He has successfully supervised master students, authored publications in international journals and conference proceedings. He is also a member of Nigerian Computer Society (NCS), Internet Society Organisation (ISOC), and Nigerian Institute of Management (NIM).

Author Articles
MCS-MCMC for Optimising Architectures and Weights of Higher Order Neural Networks

By Noor Aida Husaini Rozaida Ghazali Nureize Arbaiy Ayodele Lasisi

DOI: https://doi.org/10.5815/ijisa.2020.05.05, Pub. Date: 8 Oct. 2020

The standard method to train the Higher Order Neural Networks (HONN) is the well-known Backpropagation (BP) algorithm. Yet, the current BP algorithm has several limitations including easily stuck into local minima, particularly when dealing with highly non-linear problems and utilise computationally intensive training algorithms. The current BP algorithm is also relying heavily on the initial weight values and other parameters picked. Therefore, in an attempt to overcome the BP drawbacks, we investigate a method called Modified Cuckoo Search-Markov chain Monté Carlo for optimising the weights in HONN and boost the learning process. This method, which lies in the Swarm Intelligence area, is notably successful in optimisation task. We compared the performance with several HONN-based network models and standard Multilayer Perceptron on four (4) time series datasets: Temperature, Ozone, Gold Close Price and Bitcoin Closing Price from various repositories. Simulation results indicate that this swarm-based algorithm outperformed or at least at par with the network models with current BP algorithm in terms of lower error rate.

[...] Read more.
Other Articles