Matthew Luciw

Since July 2010, I have been a postdoctoral researcher at IDSIA, in the group of Jürgen Schmidhuber.

Before that, I was a Ph.D. student at Michigan State University, where I was a member of the Embodied Intelligence lab, the group of Juyang Weng.

Research

at IDSIA

• Sohrob Kazerounian, Matthew Luciw, Mathis Richter, and Yulia Sandarmirskaya (2013). Autonomous Reinforcement of Behavioral Sequences in Neural Dynamics. In Proceedings of the International Joint Conference on Neural Networks (IJCNN, Dallas).


• Linus Gisslen, Mark Ring, Matthew Luciw, and Juergen Schmidhuber (2012). Modular Value Iteration through Regional Decomposition. In Proceedings of the Artificial General Intelligence Conference (AGI, Oxford).


• Varun Raj Kompella, Matthew Luciw, Marijn Stollenga, Leo Pape, and Juergen Schmidhuber (2012). Autonomous Learning of Abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis (Curious Dr. MISFA). In Proceedings of the International Conference on Development and Learning and Epigenetic Robotics (ICDL-EPIROB, San Diego). -[Video]-


• Varun Raj Kompella, Matthew Luciw, and Juergen Schmidhuber (2012). Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams. Neural Computation. -[Video]- -[Algorithm]- -[Code]-


• Matthew Luciw and Juergen Schmidhuber (2012). Low Complexity Proto-Value Function Learning from Sensory Observations with Incremental Slow Feature Analysis. In Proceedings of the International Conference on Artificial Neural Networks (ICANN, Lausanne). -[Longer Version]- -[Video: Value Function Adaptation]-


• Hung Ngo, Matthew Luciw, Alexander Foerster, and Juergen Schmidhuber (2012). Learning Skills from Play: Artificial Curiosity on a Katana Robot Arm. In Proceedings of the International Joint Conference on Neural Networks (IJCNN, Brisbane). -[Short "High Impact" Video]- -[Long Video With Music]- -[Slides]-


• Matthew Luciw, Varun Raj Kompella, and Juergen Schmidhuber (2012). Hierarchical Incremental Slow Feature Analysis. Workshop on Deep Hierarchies in Vision (DHV, Vienna). -[Poster]-


• Matthew Luciw, Vincent Graziano, Mark Ring, and Juergen Schmidhuber (2011). Artificial Curiosity with Planning for Autonomous Perceptual and Cognitive Development. In Proceedings of the International Conference on Development and Learning and Epigenetic Robotics (ICDL-EPIROB, Frankfurt). -[Matlab Code]- -[Poster]-


• Giuseppe Cuccu, Matthew Luciw, Juergen Schmidhuber, and Faustino Gomez (2011). Intrinsically Motivated NeuroEvolution for Vision-Based Reinforcement Learning. In Proceedings of the International Conference on Development and Learning and Epigenetic Robotics (ICDL-EPIROB, Frankfurt). -[A Few Slides]-


• Linus Gisslen, Matt Luciw, Vincent Graziano, and Juergen Schmidhuber (2011). Sequential Constant Size Compressors for Reinforcement Learning. In Proceedings of the Artificial General Intelligence Conference (AGI, Mountainview, CA). -[Best Paper Award]- -[Slides]- -[Video]- -[RAAM During Training (by Vincent Graziano)]-


• Varun Raj Kompella, Matthew Luciw, and Juergen Schmidhuber (2011). Incremental Slow Feature Analysis. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI, Barcelona). -[Code]-

at MSU

• Matthew Luciw and Juyang Weng (2010). Top–Down Connections in Self-Organizing Hebbian Networks: Topographic Class Grouping. IEEE Transactions on Autonomous Mental Development (TAMD) -[Related Poster at SFN]- -[Example Result on MNIST]- -[Related Abstract for CNS]-


• Juyang Weng and Matthew Luciw (2009). Dually Optimal Neuronal Layers: Lobe Component Analysis. IEEE Transactions on Autonomous Mental Development (TAMD) -[Matlab Code]-


• Zhengping Ji, Matthew Luciw, Juyang Weng, and Shuqing Zeng (2011). Incremental Online Object Learning in a Vehicular Radar-Vision Fusion Framework. IEEE Transactions on Intelligent Transportation Systems (IEEE-ITS) -[Video]-


• Juyang Weng and Matthew Luciw (2011). Brain-Like Emergent Spatial Processing. IEEE Transactions on Autonomous Mental Development (TAMD) -[Matlab Code]-


• Matthew Luciw and Juyang Weng (2010). Where-What Network 4: The Effect of Multiple Internal Areas. In Proceedings of the International Conference on Development and Learning (ICDL, Ann Arbor).


• Matthew Luciw and Juyang Weng (2010). Where-What Network 3: Developmental Top-Down Attention for Multiple Foregrounds and Complex Backgrounds. In Proceedings of the International Joint Conference on Neural Networks (IJCNN, Barcelona). -[Matlab Code]- -[Slides]-


• Matthew Luciw and Juyang Weng (2009). Laterally Connected Lobe Component Analysis: Precision and Topography. In Proceedings of the International Conference on Development and Learning (ICDL, Shanghai). -[Slides]-


• Matthew Luciw and Juyang Weng (2008). Topographic Class Grouping with Applications to 3D Object Recognition. In Proceedings of the International Joint Conference on Neural Networks (IJCNN, Hong Kong). -[Slides]-


• Matthew Luciw, Juyang Weng, and Shuqing Zeng (2008). Motor Initiated Expectation Through Top-Down Connections as Abstract Context in a Physical World. In Proceedings of the International Conference on Development and Learning (ICDL, Monterey).


• Laura Grabowski, Matthew Luciw, and Juyang Weng (2007). A System for Epigenetic Concept Development through Autonomous Associative Learning. In Proceedings of the International Conference on Development and Learning (ICDL, London). -[Poster]-


• Hanqing Zhao, Zhengping Ji, Matthew Luciw, and Juyang Weng (2007). Developmental Learning for Avoiding Dynamics Obstacles Using Attention. In Proceedings of the International Conference on Development and Learning (ICDL, London).


• Zhengping Ji, Matthew Luciw, Shuqing Zeng, and Varsha Sadekar (2007). A Biologically-Motivated Developmental System towards Perceptual Awareness in Vehicle-Based Robots. In Proceedings of the International Conference on Epigenetic Robotics (EPIROB, Rutgers).


• Juyang Weng and Matthew Luciw (2006). Optimal In-Place Self-Organization for Cortical Development: Limited Cells, Sparse Coding, and Cortical Topography. In Proceedings of the International Conference on Development and Learning (ICDL, Bloomington).


• Matthew Luciw and Zhengping Ji (2006). Building Blocks of Development. In IEEE Computational Intelligence Magazine.

(More about my Ph.D. research.).

Projects

• Neural Dynamics. "A neuro-dynamic framework for cognitive robotics: Autonomous generation of scene representations and behavioral sequences using online learning". 2011-2015. EU FP7-ICT programme.
• State representation in reward based learning – from spiking neuron models to psychophysics. 2008-2012. SNSF, Sinergia grant.

Random