Find Academic Supervisors

David LipshutzView profile

Assistant Professor

• Neural Computation
• Theoretical Neuroscience
• Efficient Coding
• +5 more

David Lipshutz is an Assistant Professor of Neuroscience at Baylor College of Medicine and holds an adjunct appointment as Assistant Professor in Electrical and Computer Engineering at Rice University. His research focuses on understanding how large neural populations coordinate to compute efficiently and robustly, with applications in theoretical neuroscience and machine learning. Education: BA and PhD in Mathematics from UC San Diego. Postdoctoral training includes positions in Applied Mathematics at Brown University and Electrical Engineering at the Technion. Research interests span neural computation, synaptic plasticity, adaptive coding mechanisms, and the intersection of neuroscience with machine learning. The Lipshutz Lab develops algorithmic frameworks linking neural dynamics to learning objectives, emphasizing non-Hebbian plasticity and efficient coding principles. Key awards include the Best Paper Award at UniReps 2024 and an ICLR 2025 oral presentation. His work has been recognized for contributions to optimal transport methods in neural representation comparison and interneuron-driven adaptive coding. Advising includes graduate students at Rice University and postdoctoral researchers at Baylor, with a focus on interdisciplinary training bridging mathematics, engineering, and neuroscience.

Laurenz WiskottView profile

Professor

• Machine Learning
• Computational Neuroscience
• Neural Networks
• +4 more

Laurenz Wiskott is a Professor of Computer Science at the Ruhr-Universität Bochum (RUB), leading the Theory of Neural Systems group at the Institut für Neuroinformatik. His research focuses on machine learning, computational neuroscience, and neuro-inspired AI. He holds affiliations with multiple departments including the Department of Physics and Astronomy, Research Department of Neuroscience, and the International Graduate School of Neuroscience. Wiskott earned his PhD in Physics from RUB in 1995, followed by postdoctoral research at the Salk Institute and Humboldt University Berlin. He has authored over 100 publications, including influential work on Slow Feature Analysis (SFA) and its applications in vision, memory, and reinforcement learning. Notable awards include the 'Best Paper Award' at Machine Learning conferences and recognition for his educational tools like the student advising dashboard. His teaching spans courses on machine learning, computational neuroscience, and AI fundamentals. Current projects include explainable AI, curriculum analytics, and neuro-inspired RL efficiency. Education: PhD in Physics (1995), Ruhr-Universität Bochum Diploma in Physics (1990), University of Osnabrück Studies in Physics (1985–1989), University of Göttingen Research Interests: Slow Feature Analysis, generative models of episodic memory, reinforcement learning, human-centered AI ethics, curriculum analytics, and neuro-inspired machine learning architectures. Grants & Projects: Leads the HUMAINE (Human-Centered AI) initiative and contributed to EU-funded projects like NET-humAIn. Active in educational tech through KI:edu.nrw, developing dashboards for student advising. Labs/Teams: Directs the Theory of Neural Systems lab at INI, collaborating with the Center for Mind and Cognition and the Machine Learning & AI group at RUB.

Aditya GilraView profile

Researcher

• Computational Neuroscience
• Control Theory
• Machine Learning
• +3 more

Dr. Aditya Gilra is a Researcher in the Machine Learning Group at Centrum Wiskunde & Informatica (CWI), Amsterdam, Netherlands, since February 2022. He is also a Visiting Academic at the University of Sheffield, UK. Previously, he held positions including Lecturer (Assistant Professor) at the University of Sheffield (2020-2022), ISTplus Marie Skłodowska-Curie Fellow at Institute of Science and Technology Austria (2019), and postdoctoral researcher roles at University of Bonn, EPFL, and others. His research focuses on computational neuroscience, control theory, and machine learning. Education: PhD in Computational Neuroscience from National Centre for Biological Sciences (NCBS), TIFR, Bangalore (2015) MSc in Physics from TIFR Mumbai (2009) Bachelor's in Electrical & Electronics Engineering from IIT Madras (1996) Research Interests: Neuroscience and Machine Learning interface, particularly motor and cognitive learning Biologically plausible spiking neural networks and reinforcement learning Applications in neuromorphic computing and control theory Publications highlight contributions to neuromorphic systems, reservoir computing, and theoretical neuroscience. Key areas include predictive models for non-linear dynamics and cognitive flexibility mechanisms. Grants include the EPSRC-funded "CausalXRL" project (2021-2024). Collaborations span institutions like IST Austria, University of Bonn, and Sheffield. Labs: Active in CWI's Machine Learning Group and affiliated with Sheffield's Neuroscience Institute.

Elahe AraniView profile

Assistant Professor

• Continual Learning
• Self-Supervised Learning
• Scene Understanding
• +6 more

Elahe Arani is an Assistant Professor in the Department of Mathematics and Computer Science at Eindhoven University of Technology. She also holds external positions as Head of AI Research at Wayve (since October 2023) and previously served as Senior AI Manager and Senior Research Scientist at Wayve from September 2020 to September 2023. Her research interests are centered around Continual Learning, Self-Supervised Learning, and Learning under Noisy Labels. She focuses on developing algorithms for efficient, reliable, and adaptable AI models, particularly in the context of Scene Understanding and Multi-Task Learning. Her work also explores the application of AI in Autonomous Vehicles and integrates insights from Neuroscience to design more biologically plausible AI systems. Key areas include improving generalization in neural networks, mitigating catastrophic forgetting, and leveraging shape-awareness for robust model training. Elahe Arani's recent publications highlight advancements in Continual Learning and Self-Supervised Learning techniques, with a focus on improving model efficiency and adaptability. Her work also delves into applications for Autonomous Vehicles, such as vision-language alignment in SimLingo and generative world models in Gaia-2. She has contributed to frameworks addressing catastrophic forgetting and neural network optimization, often combining biological plausibility with computational methods. No scientific awards are explicitly mentioned in the provided text. No supervised students or specific grant information is listed. Her research emphasizes practical applications and theoretical contributions to AI, with a notable focus on reducing data dependency and environmental impact through efficient model designs. While no specific lab or team names are mentioned, her research involves collaborations in AI-driven systems, including work on road maintenance inspection and autonomous driving technologies. These collaborations aim to bridge academic and industry applications of AI.

• Neuromorphic Computing
• Vector Symbolic Architectures
• Reinforcement Learning
• +7 more

Michael Furlong is an Adjunct Assistant Professor at the University of Waterloo. His research bridges neuroscience and computer science, focusing on neuromorphic computing , vector symbolic architectures , and autonomous robotic systems . He has contributed to frameworks like Neurobench for evaluating neuromorphic algorithms and developed models for cognitive processes such as visual attention and action specification. Email: michael.furlong@uwaterloo.ca Research Interests : His work explores biologically plausible computation , spiking neural networks , and Bayesian optimization . Publications highlight autonomous exploration , terrain classification , and information-gathering strategies for planetary missions. Collaborative projects emphasize fair benchmarking and robust adaptive recovery in robotic systems. Recent Trends : Recent articles focus on hyperdimensional computing , probabilistic neuromorphic programming , and multi-modal active perception . These studies integrate category theory , dynamic modeling , and semantic processing to advance neuromorphic hardware and cognitive architectures. Key Collaborations : Participated in planetary exploration initiatives, including lunar rover simulation and icy moon landing site selection , combining Wald's sequential probability ratio test for fault tolerance and neural predictive control for robotic chassis reconfiguration.

Thomas A. ClelandView profile

Professor

• Neuroscience
• Cognitive Neuroscience
• Olfactory Systems
• +3 more

Thomas A. Cleland is a Professor of Psychology at Cornell University, affiliated with the College of Arts and Sciences. His research focuses on how cognitive and perceptual processes emerge from neural circuit properties, particularly in olfactory systems. He explores learning, memory, and sensory processing using techniques like electrophysiology, computational modeling, and neuromorphic algorithms. Cleland's work bridges neuroscience and artificial intelligence, aiming to develop biologically inspired solutions for AI systems. He teaches courses such as PSYCH 4600 (Neural Representations) and leads the Computational Physiology Laboratory. His research integrates interdisciplinary methods, including brain imaging (e.g., light-sheet imaging), behavior genetics, and theoretical studies. Cleland’s lab collaborates on projects like odor recognition, neuromorphic circuits, and neural oscillations, with publications spanning journals like Neuroscience and Artificial Intelligence . His contributions include developing tools such as the Annolid segmentation framework and advancing understanding of olfactory bulb dynamics. Cleland’s work has implications for AI, sensory neuroscience, and neurotechnology, reflecting his commitment to linking biological insights with computational innovation.

Aran NayebiView profile

Assistant Professor

• Machine Learning
• Neuroscience
• Artificial Intelligence
• +5 more

Aran Nayebi is an Assistant Professor at Carnegie Mellon University, affiliated with the Machine Learning & Neuroscience Institute. His research focuses on integrating machine learning and neuroscience to understand biological intelligence and develop biologically plausible AI models. He explores embodied agents, neural network dynamics, and human-AI alignment through game-theoretic frameworks. Key research interests include reverse-engineering natural intelligence through embodied agents, developing models that align with brain dynamics (e.g., zebrafish agents, rodent tactile processing), and addressing ethical challenges in AI alignment. His work bridges computational neuroscience and neural network design, emphasizing scalable models and biologically inspired algorithms. Recent publications span topics such as AI-driven economic policy (Universal Basic Income), neuroAI turing tests, and model-brain comparison techniques. His interdisciplinary approach addresses both technical challenges (e.g., neural network scaling) and societal implications of AI.

Spyros SamothrakisView profile

Senior Lecturer

• Reinforcement Learning
• Machine Learning
• Neural Networks
• +3 more

Dr. Spyros Samothrakis is a Senior Lecturer and Chief Scientific Adviser at the School of Computer Science and Electronic Engineering, University of Essex. His primary roles include academic research and advisory work in artificial intelligence and machine learning. He holds a PhD in Computer Science from the University of Essex, an MSc in Intelligent Systems from the University of Sussex, and a BSc in Computer Science from the University of Sheffield. His research focuses on Reinforcement Learning (RL) , Machine Learning (ML) , Neural Networks , and Role-Playing Games (RPGs) . He explores applications in areas like causal inference, game theory, and supply chain management. Recent work includes developing frameworks for automated cost estimation in games and analyzing AI agents in complex socioeconomic systems. Notable contributions include studies on self-play algorithms, causal structure learning, and the societal implications of AI. His articles span topics from neurocontrol optimization to ethical considerations in AI deployment. Dr. Samothrakis advises PhD students in computer science and has supervised research on causal effect estimation, memory-driven exploration, and text generation. He has secured grants from organizations like the Alan Turing Institute and the ESRC for projects involving AI in micro-social change and data-driven decision-making. His collaborations extend to industry partners such as the National Theatre and NHS Trusts, applying AI to healthcare and cultural data analysis. He actively contributes to conferences and publishes in top-tier journals like Neural Networks and IEEE Transactions .

Wolfgang MaassView profile

Professor

• Neural Networks
• Machine Learning
• Computational Neuroscience
• +3 more

Wolfgang Maass is a Professor at the Institute of Machine Learning and Neural Computation at Technische Universität Graz . His research focuses on computational neuroscience, neuromorphic engineering, and machine learning, with an emphasis on understanding how biological neural networks process information and inspire artificial systems. He has contributed extensively to the development of spiking neural networks, synaptic plasticity models, and neuromorphic hardware. Education: Dipl.-Ing. (Diploma in Engineering), Dr.rer.nat. (PhD in Natural Sciences) Affiliations: Institute of Machine Learning and Neural Computation, TU Graz Key research interests include: Neural network models for cognitive functions Biologically plausible learning algorithms Neuromorphic computing and hardware implementations Computational principles of cortical microcircuits Recent work highlights the integration of biological principles into artificial intelligence, including studies on synaptic plasticity (BTSP), spiking neural networks for image recognition, and energy-efficient neuromorphic systems. His research bridges theoretical neuroscience and applied machine learning, with a focus on systems that emulate brain-like functionality. He has presented at major conferences such as the International Convention on the Mathematics of Neuroscience and AI and has authored over 200 publications. His work has been recognized for its interdisciplinary impact, advancing both neuroscience and AI fields.

• Computational Neuroscience
• Theoretical Neuroscience
• Multisensory Integration
• +9 more

Wenhao Zhang is an Assistant Professor in the Lyda Hill Department of Bioinformatics at UT Southwestern Medical Center, with a secondary appointment in the Peter O’Donnell Jr. Brain Institute. He holds the Lupe Murchison Foundation Scholar in Medical Research award. His research bridges computational neuroscience and biomedicine, focusing on neural circuits' role in information processing and developing brain-inspired algorithms. He collaborates with experimental neuroscientists, psychologists, and computer scientists to translate theoretical insights into practical applications. Education: B.E. in Biomedical Engineering from Shanghai Jiao Tong University (2009), Ph.D. in Theoretical Neuroscience from the Institute of Neuroscience, Chinese Academy of Sciences (2016). Postdoctoral training includes the University of Chicago (2020–2021), University of Pittsburgh (2018–2020), Carnegie Mellon University (2016–2017), and Hong Kong University of Science and Technology (2015–2016). Research interests center on biologically plausible normative theories for information processing in neural circuits and artificial systems. Key areas include Bayesian inference, multisensory integration, neural circuit dynamics, and the development of brain-inspired machine learning algorithms. His work employs methods like nonlinear dynamics, Bayesian inference, and information theory to study how perception and decision-making emerge from neural circuits. Recent publications emphasize theoretical frameworks for neural computation, such as motion planning circuits using Lie group theory, inhibitory interneurons' role in Bayesian sampling efficiency, and grid cells' spatial representation mechanisms. His lab also explores place cell dynamics and recurrent network models for equivariant representations. Scientific Award: Lupe Murchison Foundation Scholar in Medical Research Zhang advises PhD students including Armand Rathgeb, Zimei Chen, Yi Ren, and Eryn Sale, as well as visiting scholars like Junfeng Zuo and Xinruo Yang. His lab collaborates with institutions such as UCLA, Peking University, and the University of Rochester. Funding includes travel grants for students, e.g., Eryn Sale’s 2024 Cosyne award. He directs the Computational Neuroscience Lab (CNL) at UT Southwestern, which combines normative theories with biologically detailed models to study neural circuit principles underlying cognition. The lab actively pursues interdisciplinary research, using techniques from mathematics and computer science to inform experimental neuroscience and vice versa.

• Computational Neuroscience
• Reinforcement Learning
• Machine Learning
• +3 more

Peter Dayan serves as Managing Director and Professor in the Department of Computational Neuroscience at the Max Planck Institute for Biological Cybernetics in Tübingen, Germany, where he leads research initiatives at the intersection of neuroscience and artificial intelligence. His position encompasses strategic oversight of the department's scientific direction and operational management. Dr. Dayan's research program fundamentally explores computational principles of brain function, with concentrated expertise in reinforcement learning algorithms, decision-making processes, and neural network modeling. His work bridges theoretical machine learning frameworks with biological plausibility, particularly investigating how Bayesian inference and predictive coding operate in neural systems. This cross-disciplinary approach has established foundational contributions to understanding learning mechanisms in both biological and artificial agents. As head of the Department of Computational Neuroscience, he directs a research ecosystem focused on decoding neural computation through mathematical modeling, simulation, and experimental collaboration. The department maintains strong ties with Tübingen's neuroscience community and international AI research networks, fostering innovation in neuro-inspired computing architectures and cognitive modeling frameworks.

• Applied Mathematics
• Computational Neuroscience
• Mathematical Biology
• +4 more

Thoa Thieu is an Assistant Professor at the School of Mathematical and Statistical Sciences and College of Health Professions at the University of Texas Rio Grande Valley. She holds email addresses at thoa.thieu@utrgv.edu and thoathieu28@gmail.com . Dr. Thieu's education includes a Double Ph.D. in Mathematics from Gran Sasso Science Institute (Italy) and Karlstad University (Sweden), supervised by Prof. Adrian Muntean and Dr. Matteo Colangeli. She earned a Master's in Applied Mathematics from the University of Orleans and Tours (France), and a B.S. in Mathematics and Statistics from the University of Science in Vietnam. Her research focuses on stochastic systems modeling with applications in: Neuroscience (neuronal dynamics, synaptic plasticity) Crowd behavior analysis (pedestrian flows, active-passive interactions) Biological systems (insulin transport in beta cells, cellular cytoskeleton dynamics) Interdisciplinary computational methods (coupled Skorokhod SDEs, lattice gas frameworks) Her recent work emphasizes multi-fidelity modeling and well-posedness analysis in complex systems. She has contributed to neuromorphic computing applications and disaster-evacuation simulations through her mathematical frameworks. Professional experience includes Postdoctoral Fellowships at Indiana University (2023-2024) under Dr. William Holmes, and at Wilfrid Laurier University (2021-2022) under Prof. Roderick Melnik. Her research outputs bridge pure mathematics (stochastic PDEs, uniqueness proofs) with applied domains in health sciences and social dynamics.

Konstantinos MichmizosView profile

Associate Professor

• Neuromorphic Computing
• Artificial Intelligence
• Computational Neuroscience
• +4 more

Konstantinos Michmizos is an Associate Professor in the Department of Computer Science at Rutgers University, with affiliations to the Rutgers Center for Cognitive Science, Brain Health Institute, and Center for Computational Biomedicine Imaging and Informatics. His research focuses on neuromorphic computing, neuro-AI integration, and brain-inspired robotics, emphasizing systems that interact with brain activity across neural and behavioral scales. He leads the Michmizos Lab and ComBra Lab, pioneering projects like robotic nurses powered by neuromorphic chips and astrocyte-driven computational models. Key research interests include neuromorphic hardware-software co-design, spiking neural networks, and applications in neurorehabilitation. Notable achievements include securing grants from NIH, Intel, and VCRI, along with awards for best papers on Neuro-AI and computational astrocyence. His work bridges artificial intelligence with biological systems, aiming to translate neural mechanisms into advanced robotic and biomedical technologies. Michmizos teaches graduate courses like Brain-Inspired Computing and has advised students such as Ioannis Polykretis. His research spans neuromorphic SLAM systems, EEG decoding frameworks, and biohybrid robotic systems, with recent breakthroughs in calcium wave modeling for astrocyte-neuron interactions. Collaborations emphasize multi-scale computational biology and clinical applications in neurology.

• Complex Adaptive Systems
• Collective Behavior
• Organismal Biology
• +9 more

Ted Pavlic is an Associate Professor at Arizona State University (ASU), jointly appointed in the School of Computing and Augmented Intelligence and the School of Life Sciences. His interdisciplinary research bridges engineering and biology, focusing on adaptive decision-making in natural and artificial systems. He leads the BEET lab, which studies collective behavior in social insects and designs bio-inspired algorithms for robotics and AI. Education: Ph.D. in Electrical and Computer Engineering (The Ohio State University, 2010), postdoctoral training in life sciences and computer science (ASU and OSU). Former industry roles include software engineering and analog electronics. Research interests include complex adaptive systems, social insect behavior, optimal foraging theory, AI, and biomimicry. He has mentored over 20 students and postdocs, leading to impactful work in swarm robotics, collective intelligence, and sustainability. Key awards: SWARM 2021 Best Paper Award, invited TEDx speaker. Active in professional organizations like the Animal Behavior Society and the Entomological Society of America. Grants include NSF-funded projects on sleep-dependent learning in AI and biomimetic control systems. Collaborates across ASU’s complexity initiatives, including the Biomimicry Center and the Center for Social Dynamics and Complexity. Lab affiliations: BEET Lab, ASU-SFI Center for Biosocial Complex Systems. Engages in public outreach through YouTube, Twitter, and Mastodon.

• Machine Learning
• Neuroscience
• Cyber-Physical Systems
• +3 more

Peyman Mohseni Kiasari is a PreDoc Researcher at the Cyber-Physical Systems institute (E191-01) of Vienna University of Technology, focusing on interdisciplinary research blending Machine Learning and Neuroscience . Currently working on the MATTO-GBM project (2024–2027), he investigates depthwise convolutional architectures for their biological plausibility and interpretability. Active in Computer Vision and Neural Network Optimization Contributing to research on Biological Receptive Fields and Kernel Clustering His work bridges computational models with neuroscientific principles, aiming to enhance AI systems' transparency and biological alignment. Recent publications highlight trends in depthwise convolutional kernels for feature extraction and neural network interpretability . Current affiliations: Vienna University of Technology (Cyber-Physical Systems, E191-01).