Simon Khan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Simon Khan has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Chris Yakopcic
Department of Electrical and Computer Engineering, University of Dayton, Dayton, OH 45469, USA
2 shared publications - Garrett E. Katz
Syracuse University
2 shared publications - Mark Barnell
Air Force Research Laboratory Information Directorate, Rome, NY, USA
2 shared publications - Qing Wu
Air Force Research Laboratory Information Directorate, Rome, United States, USA
2 shared publications - Qinru Qiu
Syracuse University
2 shared publications - Shahanur Alam
Department of Electrical and Computer Engineering, University of Dayton, Dayton, OH 45469, USA
2 shared publications
Latest Publications
- Open Access
Predictive Auxiliary Learning for Belief-based Multi-Agent Systems
The performance of multi-agent reinforcement learning (MARL) in partially observable environments depends on effectively aggregating information from observations, communications, and reward signals. While most existing multi-agent systems primarily rely on rewards as the only feedback for policy training, our research shows that introducing auxiliary predictive tasks can significantly enhance learning efficiency and stability. We propose Belief-based Predictive Auxiliary Learning (BEPAL), a framework that incorporates auxiliary training objectives to support policy optimization. BEPAL follows the centralized training with decentralized execution paradigm. Each agent learns a belief model that predicts unobservable state information, such as other agents' rewards or motion directions, alongside its policy model. By enriching hidden state representations with information that does not directly contribute to immediate reward maximization, this auxiliary learning process stabilizes MARL training and improves overall performance. We evaluate BEPAL in the predator-prey environment and Google Research Football, where it achieves an average improvement of about 16 percent in performance metrics and demonstrates more stable convergence compared to baseline methods.
Open AccessPredictive Auxiliary Learning for Belief-based Multi-Agent Systems
The performance of multi-agent reinforcement learning (MARL) in partially observable environments depends on effectively aggregating information from observations, communications, and reward signals. While most existing multi-agent systems primarily rely on rewards as the only feedback for policy training, our research shows that introducing auxiliary predictive tasks can significantly enhance learning efficiency and stability. We propose Belief-based Predictive Auxiliary Learning (BEPAL), a framework that incorporates auxiliary training objectives to support policy optimization. BEPAL follows the centralized training with decentralized execution paradigm. Each agent learns a belief model that predicts unobservable state information, such as other agents' rewards or motion directions, alongside its policy model. By enriching hidden state representations with information that does not directly contribute to immediate reward maximization, this auxiliary learning process stabilizes MARL training and improves overall performance. We evaluate BEPAL in the predator-prey environment and Google Research Football, where it achieves an average improvement of about 16 percent in performance metrics and demonstrates more stable convergence compared to baseline methods.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 655-663
Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learning
Reinforcement learning (RL) has demonstrated remarkable success in solving complex decision-making problems, yet its adoption in critical domains is hindered by the lack of interpretability in its decision-making processes. Existing explainable AI (xAI) approaches often fail to provide meaningful explanations for RL agents, particularly because they overlook the contrastive nature of human reasoning—answering "why this action instead of that one?" To address this gap, we propose a novel framework of contrastive learning to explain RL selected actions, named VisionMask. VisionMask is trained to generate explanations by explicitly contrasting the agent's chosen action with alternative actions in a given state using a self-supervised manner. We demonstrate the efficacy of our method through experiments across diverse RL environments, evaluating it in terms of faithfulness, robustness and complexity. Our results show that VisionMask significantly improves human understanding of agent behavior while maintaining accuracy and fidelity. Furthermore, we present examples illustrating how VisionMask can be used for counterfactual analysis. This work bridges the gap between RL and xAI, paving the way for safer and more interpretable RL systems.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 1, 655-663
Open AccessWhy the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learning
Reinforcement learning (RL) has demonstrated remarkable success in solving complex decision-making problems, yet its adoption in critical domains is hindered by the lack of interpretability in its decision-making processes. Existing explainable AI (xAI) approaches often fail to provide meaningful explanations for RL agents, particularly because they overlook the contrastive nature of human reasoning—answering "why this action instead of that one?" To address this gap, we propose a novel framework of contrastive learning to explain RL selected actions, named VisionMask. VisionMask is trained to generate explanations by explicitly contrasting the agent's chosen action with alternative actions in a given state using a self-supervised manner. We demonstrate the efficacy of our method through experiments across diverse RL environments, evaluating it in terms of faithfulness, robustness and complexity. Our results show that VisionMask significantly improves human understanding of agent behavior while maintaining accuracy and fidelity. Furthermore, we present examples illustrating how VisionMask can be used for counterfactual analysis. This work bridges the gap between RL and xAI, paving the way for safer and more interpretable RL systems.
- Open Access
Linearithmic Clean-up for Vector-Symbolic Key-Value Memory with Kroneker Rotation Products
A computational bottleneck in current Vector-Symbolic Architectures (VSAs) is the ``clean-up'' step, which decodes the noisy vectors retrieved from the architecture. Clean-up typically compares noisy vectors against a ``codebook'' of prototype vectors, incurring computational complexity that is quadratic or similar. We present a new codebook representation that supports efficient clean-up, based on Kroneker products of rotation-like matrices. The resulting clean-up time complexity is linearithmic, i.e. $\mathcal{O}(N\,\text{log}\,N)$, where $N$ is the vector dimension and also the number of vectors in the codebook. Clean-up space complexity is $\mathcal{O}(N)$. Furthermore, the codebook is not stored explicitly in computer memory: It can be represented in $\mathcal{O}(\text{log}\,N)$ space, and individual vectors in the codebook can be materialized in $\mathcal{O}(N)$ time and space. At the same time, asymptotic memory capacity remains comparable to standard approaches. Computer experiments confirm these results, demonstrating several orders of magnitude more scalability than baseline VSA techniques.Open AccessLinearithmic Clean-up for Vector-Symbolic Key-Value Memory with Kroneker Rotation Products
A computational bottleneck in current Vector-Symbolic Architectures (VSAs) is the ``clean-up'' step, which decodes the noisy vectors retrieved from the architecture. Clean-up typically compares noisy vectors against a ``codebook'' of prototype vectors, incurring computational complexity that is quadratic or similar. We present a new codebook representation that supports efficient clean-up, based on Kroneker products of rotation-like matrices. The resulting clean-up time complexity is linearithmic, i.e. $\mathcal{O}(N\,\text{log}\,N)$, where $N$ is the vector dimension and also the number of vectors in the codebook. Clean-up space complexity is $\mathcal{O}(N)$. Furthermore, the codebook is not stored explicitly in computer memory: It can be represented in $\mathcal{O}(\text{log}\,N)$ space, and individual vectors in the codebook can be materialized in $\mathcal{O}(N)$ time and space. At the same time, asymptotic memory capacity remains comparable to standard approaches. Computer experiments confirm these results, demonstrating several orders of magnitude more scalability than baseline VSA techniques. - Open Access
- 29 July 2024
- Published by MDPI AG in Electronics
- Vol. 13 (15) , 2988
Survey of Deep Learning Accelerators for Edge and Emerging Computing
The unprecedented progress in artificial intelligence (AI), particularly in deep learning algorithms with ubiquitous internet connected smart devices, has created a high demand for AI computing on the edge devices. This review studied commercially available edge processors, and the processors that are still in industrial research stages. We categorized state-of-the-art edge processors based on the underlying architecture, such as dataflow, neuromorphic, and processing in-memory (PIM) architecture. The processors are analyzed based on their performance, chip area, energy efficiency, and application domains. The supported programming frameworks, model compression, data precision, and the CMOS fabrication process technology are discussed. Currently, most commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the attention of the industry in recent years. Neuromorphic processors are highly efficient for performing computation with fewer synaptic operations, and several neuromorphic processors offer online training for secured and personalized AI applications. This review found that the PIM processors show significant energy efficiency and consume less power compared to dataflow and neuromorphic processors. A future direction of the industry could be to implement state-of-the-art deep learning algorithms in emerging non-von Neumann computing paradigms for low-power computing on edge devices.
- 29 July 2024
- Published by MDPI AG in Electronics
- Vol. 13 (15) , 2988
Open AccessSurvey of Deep Learning Accelerators for Edge and Emerging Computing
The unprecedented progress in artificial intelligence (AI), particularly in deep learning algorithms with ubiquitous internet connected smart devices, has created a high demand for AI computing on the edge devices. This review studied commercially available edge processors, and the processors that are still in industrial research stages. We categorized state-of-the-art edge processors based on the underlying architecture, such as dataflow, neuromorphic, and processing in-memory (PIM) architecture. The processors are analyzed based on their performance, chip area, energy efficiency, and application domains. The supported programming frameworks, model compression, data precision, and the CMOS fabrication process technology are discussed. Currently, most commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the attention of the industry in recent years. Neuromorphic processors are highly efficient for performing computation with fewer synaptic operations, and several neuromorphic processors offer online training for secured and personalized AI applications. This review found that the PIM processors show significant energy efficiency and consume less power compared to dataflow and neuromorphic processors. A future direction of the industry could be to implement state-of-the-art deep learning algorithms in emerging non-von Neumann computing paradigms for low-power computing on edge devices.
- Open Access
- 10 July 2024
- Published by MDPI AG in Preprints.org
Survey of Deep Learning Accelerators for Edge and Emerging Computing
The unprecedented progress in Artificial Intelligence (AI), particularly in deep learning algorithms with ubiquitous internet connected smart devices, has created a high demand for AI computing on the edge devices. This review studied commercially available edge processors, and the processors that are still in industrial research stages. We categorized state-of-the-art edge processors based on the underlying architecture, such as dataflow, neuromorphic, and Processing in-Memory (PIM) architecture. The processors are analyzed based on their performance, chip area, energy efficiency, and application domains. The supported programming frameworks, model compression, data precision, and the CMOS fabrication process technology are discussed. Currently, most of the commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the industry in recent years. Neuromorphic processors are highly efficient for performing computation with fewer synaptic operations, and several neuromorphic processors offer online training for secured and personalized AI applications. This review found that the PIM processors show significant energy efficiency and consume less power compared to dataflow and neuromorphic processors. The future direction of the industry would be to implement state-of-the-art deep learning algorithms in emerging non-Von Neumann computing paradigms for low power computing on the edge devices.
- 10 July 2024
- Published by MDPI AG in Preprints.org
Open AccessSurvey of Deep Learning Accelerators for Edge and Emerging Computing
The unprecedented progress in Artificial Intelligence (AI), particularly in deep learning algorithms with ubiquitous internet connected smart devices, has created a high demand for AI computing on the edge devices. This review studied commercially available edge processors, and the processors that are still in industrial research stages. We categorized state-of-the-art edge processors based on the underlying architecture, such as dataflow, neuromorphic, and Processing in-Memory (PIM) architecture. The processors are analyzed based on their performance, chip area, energy efficiency, and application domains. The supported programming frameworks, model compression, data precision, and the CMOS fabrication process technology are discussed. Currently, most of the commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the industry in recent years. Neuromorphic processors are highly efficient for performing computation with fewer synaptic operations, and several neuromorphic processors offer online training for secured and personalized AI applications. This review found that the PIM processors show significant energy efficiency and consume less power compared to dataflow and neuromorphic processors. The future direction of the industry would be to implement state-of-the-art deep learning algorithms in emerging non-Von Neumann computing paradigms for low power computing on the edge devices.