Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
The Unreasonable Effectiveness of Scale
Published:
Scaling laws describe the relationship between a model’s performance and the scale of three key ingredients: the number of model parameters, the size of the dataset, and the amount of computational power used for training. The core finding is that as you increase these resources, the model’s performance improves in a predictable, power-law fashion. Read more
A Technical Deep Dive into Exploding Gradients
Published:
I remember one of the experiences I had duing my MS in Computer Science at Georgia Tech while working on a CNN for protein data. I was feeding raw protein data as an image, with pixel values in the standard 0-255 range, directly into the network. My model’s accuracy was stuck below 20%, and the loss was oscillating wildly. After hours of debugging, I traced the issue to its source: I had neglected to normalize my input data, leading to a classic case of “exploding gradients.” Read more
Why Randomized Optimization Needs Quantum Computing
Published:
Randomized optimization algorithms like Genetic Algorithms (GA), Simulated Annealing (SA), and Randomized Hill Climbing (RHC) are powerful tools for solving problems where traditional gradient-based methods fail. These “black-box” problems are common in fields like logistics, engineering design, and machine learning, where the optimization landscape is complex, non-differentiable, or riddled with local minima. Read more
Why Backprop Isn’t Magic: The Challenge of Local Minima
Published:
Backpropagation is the cornerstone algorithm powering much of the deep learning revolution. Coupled with gradient descent, it allows us to train incredibly complex neural networks on vast datasets. However, it’s not a silver bullet. One of the fundamental challenges that can prevent backpropagation from finding the best possible solution is the presence of local minima in the optimization landscape. Read more
DeepSeek R1: Pioneering Reasoning in Large Language Models Through Reinforcement Learning
Published:
The development of reasoning capabilities in large language models (LLMs) is a complex yet pivotal frontier in AI research. DeepSeek R1 represents a major leap in this space, introducing innovative methodologies for reasoning-oriented model training. In this post, we’ll explore what makes DeepSeek R1 significant, its architectural innovations, and its implications for the future of AI. Read more
Unveiling a $500 Billion Leap in AI: Trump’s Private Sector Investment Plan
Published:
President Donald Trump is set to announce a monumental private sector initiative aimed at bolstering the United States’ artificial intelligence (AI) infrastructure with an investment of up to $500 billion. This ambitious plan involves leading tech companies like OpenAI, SoftBank, and Oracle, under a collaborative venture named “Stargate.” Read more
Supervised Learning Showdown: kNN, SVM, Neural Networks, and Boosted Trees
Published:
In this post, we dive into the world of supervised learning, comparing the performance of four popular algorithms: k-Nearest Neighbors (kNN), Support Vector Machines (SVM), Neural Networks (NN), and Decision Trees with Boosting (specifically, AdaBoost). We’ll analyze their effectiveness on two distinct datasets, highlighting their strengths and weaknesses. Read more
Algorithm — Generate Parentheses: Python and C++ Solutions
Published:
In this blog post, we’ll explore LeetCode’s “Generate Parentheses” problem and present two clean backtracking solutions—one in Python and one in C++. This classic problem is an excellent demonstration of how to use recursion to systematically explore all valid possibilities. Read more
Meta Releases Llama 3.1 Models
Published:
Meta just released a new collection of Llama 3.1 models in 8B, 70B, and 405B parameter sizes. Read more
Algorithm — Reverse Only Letters: A Python Solution
Published:
In many programming interviews, candidates encounter challenges that test their ability to manipulate strings efficiently. One such problem involves reversing a string with a twist: only the letters should be reversed, while non-letter characters remain in their original positions. In this blog post, we’ll explore this problem and present an optimized Python solution. Read more
Training Your Own GPT Models: A Case Study
Published:
Training Read more
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Read more
Portfolio item number 2
Short description of portfolio item number 2 Read more
publications
Deep data analysis for COVID-19 outbreak
Published in Reinvention of health applications with IoT, 2022
The rampaging effects of the coronavirus disease in 2019 (COVID-19), which was pronounced a pandemic on 11 March 2020 by the World Health Organization (WHO), have become one of the biggest challenges of the twenty-first century in terms of general wellbeing and safety. Read more
Recommended citation: O.J. Odeyemi, S.O. Owoeye, K.I. Adenuga and C.B. Emele. (2022). Deep machine learning for Sensing, Analysis, and Interpretation in IoT Healthcare. Reinvention of health applications with IoT: 1-16.
Download Paper
Deep machine learning for Sensing, Analysis, and Interpretation in IoT Healthcare
Published in Reinvention of Health Applications with IoT, 2022
The introduction of the Internet of Things (IoT) has brought about a much-needed upgrade in healthcare industry worldwide. As the world population continues to increase, data generated in these industries are now collected and transmitted seamlessly over the internet, leading to a more efficient system while reducing healthcare costs. Read more
Recommended citation: O.J. Odeyemi, S.O. Owoeye, K.I. Adenuga and C.B. Emele. (2022). Deep machine learning for Sensing, Analysis, and Interpretation in IoT Healthcare. Reinvention of health applications with IoT: 1-16.
Download Paper
A human factor approach to distribution network design for e-commerce in supply chain system: a case study
Published in Enterprise Information Systems, 2023
Distribution network for e-commerce is an important supply chain (SC) networks required for effective management of warehousing. Due to the recent disruption in the SC, minimal lead times for product delivery days can no longer be guaranteed, thereby causing an increase in distribution and delivery of goods. Read more
Recommended citation: Ogbeyemi, A., Odeyemi, J., Igenewari, O., & Ogbeyemi, A. (2023). A human factor approach to distribution network design for e-commerce in supply chain system: a case study. Enterprise Information Systems, 17(12). https://doi.org/10.1080/17517575.2023.2200767.
Download Paper
Exploring the potential of computer vision and machine learning in enhancing the functionality of an EMG-controlled prosthetic hand
Published in Harvest, University of Saskatchewan, 2023
The potential of using machine learning techniques to develop prosthetic arms that can automatically perform hand gestures and grasp objects is very important in healthcare systems. Hands are an important part of the body for all vertebras, animals use theirs for locomotion, however, because of our bipedal nature as humans, we use our hands majorly for gripping and general manipulation. Read more
Recommended citation: Odeyemi, J. (2023). Exploring the potential of computer vision and machine learning in enhancing the functionality of an EMG-controlled prosthetic hand. Masters thesis, University of Saskatchewan.
Download Paper
On Automated Object Grasping for Intelligent Prosthetic Hands Using Machine Learning
Published in Bioengineering, 2024
Prosthetic technology has witnessed remarkable advancements, yet challenges persist in achieving autonomous grasping control while ensuring the user’s experience is not compromised. Read more
Recommended citation: Odeyemi, J.; Ogbeyemi, A.; Wong, K.; Zhang, W. On Automated Object Grasping for Intelligent Prosthetic Hands Using Machine Learning. Bioengineering 2024, 11, 108. https://doi.org/10.3390/bioengineering11020108.
Download Paper
A Novel Embryo Morphology Evaluation Based on Improved YOLOv8 Object Detection Model
Published in International Conference on Life System Modeling and Simulation, LSMS 2024 and International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2024, Suzhou, China, 2025
This study presents a novel approach for embryo morphology evaluation using an improved YOLOv8 object detection model, offering significant advancements in the field of reproductive medicine. Read more
Recommended citation: Talha, O., Zhou, W., Xu, Y., Liu, Q., Odeyemi, J. (2024). A Novel Embryo Morphology Evaluation Based on Improved YOLOv8 Object Detection Model. In: Gu, J., Hu, F., Zhou, H., Fei, Z., Yang, E. (eds) Robotics and Autonomous Systems and Engineering Applications of Computational Intelligence. LSMS ICSEE 2024 2024. Communications in Computer and Information Science, vol 2220. Springer, Singapore. https://doi.org/10.1007/978-981-96-0313-8_15
Download Paper
Benchmarking Randomized Optimization Algorithms on Binary, Permutation, and Combinatorial Problem Landscapes
Published in arXiv, 2025
This paper evaluates the performance of four randomized optimization algorithms across three distinct problem types, providing insights into the trade-offs between different optimization strategies. Read more
Recommended citation: Odeyemi, J., & Zhang, W. (2025). Benchmarking Randomized Optimization Algorithms on Binary, Permutation, and Combinatorial Problem Landscapes. *arXiv preprint arXiv:2501.17170*.
Download Paper
Kalman and Savitzky-Golay Filter Augmented Cnn-Lstm Framework for Predictive Maintenance in Space Manufacturing
Published in Available at SSRN, 2025
This research introduces a novel Predictive Maintenance and Scheduling (PdMS) framework specifically designed for the in-space industry, leveraging a hybrid CNN-LSTM model to accurately forecast equipment Remaining Useful Life (RUL). Read more
Recommended citation: Wong, K., Ashraf, M. A., Alzal, A., Odeyemi, J., Chipusu, K., Ip, A. W. H., Suliman, F., Khwanda, H., Liu, D. C., Zhang, W., & Yeoh, W. (2025). Kalman and Savitzky-Golay Filter Augmented Cnn-Lstm Framework for Predictive Maintenance in Space Manufacturing. *Available at SSRN 5187223*.
Download Paper
Impact of cyber physical systems on enhancing robotic system autonomy: a brief critical review
Published in The International Journal of Advanced Manufacturing Technology, 2025
This paper reviews the integration of cyber-physical systems (CPS) with robotic systems to enhance their autonomy, connectivity, and adaptability in industrial applications, addressing key challenges and potential solutions. Read more
Recommended citation: Omiyale, B.O., Odeyemi, J., Ogbeyemi, A., Olorunsogbon, F., & Zhang, W. C. (2025). Impact of cyber physical systems on enhancing robotic system autonomy: a brief critical review. *The International Journal of Advanced Manufacturing Technology, 138*, 3925–3942.
Download Paper
Mitigating 3D printing defects via cyber-physical systems: a process for fabricating defect-free components
Published in The International Journal of Advanced Manufacturing Technology, 2025
This paper reviews the impact of Cyber-Physical Systems (CPS) integration in 3D printing, focusing on its role in reducing defects and enabling real-time monitoring and control for defect-free component fabrication. Read more
Recommended citation: Omiyale, B.O., Ogedengbe, I.I., Odeyemi, J., Ogbeyemi, A., Olorunsogbon, F., & Zhang, W. C. (2025). Mitigating 3D printing defects via cyber-physical systems: a process for fabricating defect-free components. *The International Journal of Advanced Manufacturing Technology, 139*, 3175–3196.
Download Paper
Impact of cold metal transfer variants on the mechanical and microstructural properties of aluminum alloys in wire arc additive manufacturing: a critical review
Published in The International Journal of Advanced Manufacturing Technology, 2025
This critical review examines how cold metal transfer-based wire arc additive manufacturing (CMT-WAAM) addresses long-standing issues in aluminum alloy processing, focusing on managing defects and improving mechanical properties. Read more
Recommended citation: Omiyale, B.O., Jack, T.A., Ogedengbe, I.I., Odeyemi, J., Mishra, D., Ogbeyemi, A., & Zhang, W. C. (2025). Impact of cold metal transfer variants on the mechanical and microstructural properties of aluminum alloys in wire arc additive manufacturing: a critical review. *The International Journal of Advanced Manufacturing Technology, 140*, 1183–1210.
Download Paper
talks
teaching
Introduction to Mechatronics - Laboratory
Undergraduate course, University of Saskatchewan, Mechanical Engineering, 2023
This course is designed to provide students with hands-on experience in the field of mechatronics. The course will cover the basics of mechatronics, including sensors, actuators, and microcontrollers. The course will also cover the design and implementation of mechatronic systems, including the use of software tools such as MATLAB and Simulink. The course will include a series of laboratory experiments that will allow students to apply the concepts learned in class to real-world problems. Read more