Publications of Heiko Hoffmann

Publications

Peer-reviewed journal articles

Sparse Associative Memory: Heiko Hoffmann; Neural Computation, Vol. 31(5), pp. 998-1014, 2019; Available online at The MIT Press; [pdf, 584KB]
Impact of network topology on self-organized criticality: Heiko Hoffmann; Physical Review E, Vol. 97, 022313, 2018; [pdf, 719KB]
Optimization by self-organized criticality: Heiko Hoffmann and David W Payton; Scientific Reports, Vol. 8, Article no. 2358, 2018; Available online at nature.com
Suppressing cascades in a self-organized-critical model with non-contiguous spread of failures: Heiko Hoffmann and David W Payton; Chaos, Solitons & Fractals, Vol. 67, pp. 87-93, 2014; Available online at ScienceDirect; [pdf, 644KB]
Adaptive robotic tool use under variable grasps: Heiko Hoffmann, Zhichao Chen, Darren Earl, Derek Mitchell, Behnam Salemi, and Jivko Sinapov; Robotics and Autonomous Systems, Vol. 62, Issue 6, pp. 833-846, 2014; Available online at ScienceDirect; [pdf, 2.4MB]
Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors: Auke Jan Ijspeert, Jun Nakanishi, Heiko Hoffmann, Peter Pastor, and Stefan Schaal; Neural Computation, Vol. 25, No. 2, pp. 328-373, 2013; Cited by 1000+ (650+ in Scopus, most cited article in Neural Computation since 2010)
Target switching in curved human arm movements is predicted by changing a single control parameter: Heiko Hoffmann; Experimental Brain Research, Vol. 208, Issue 1, pp. 73-87, 2011; Available online at springerlink.com; [pdf, 636KB]
Grasping to Extrafoveal Targets: A Robotic Model: Wolfram Schenck, Heiko Hoffmann, and Ralf Möller; New Ideas in Psychology, Vol. 29, pp. 235-259, 2011; Available online at ScienceDirect; [pdf, 984KB]
Computational models for neuromuscular function: Francisco Valero-Cuevas, Heiko Hoffmann, Manish Kurse, Jason Kutch, and Evangelos Theodorou (all authors contributed equally); IEEE Reviews in Biomedical Engineering, Vol. 2, pp. 110-135, 2009; [pdf, 1.6M]
Local dimensionality reduction for non-parametric regression: Heiko Hoffmann, Stefan Schaal, and Sethu Vijayakumar; Neural Processing Letters, Vol. 29, pp. 109-131, 2009; The original article is available online at Springerlink.com; [pdf, 556KB]
Perception through Visuomotor Anticipation in a Mobile Robot: Heiko Hoffmann; Neural Networks, Vol. 20, pp. 22-33, 2007; Available online at ScienceDirect; [pdf, 1564KB]
Kernel PCA for Novelty Detection: Heiko Hoffmann; Pattern Recognition, Vol. 40, pp. 863-874, 2007; Available online at ScienceDirect; [pdf, 748KB]; Cited by 600+ (400+ in Scopus)
Learning visuomotor transformations for gaze-control and grasping: Heiko Hoffmann, Wolfram Schenck, Ralf Möller; Biological Cybernetics, Vol. 93, pp. 119-130, 2005; Available online at springerlink.com; [pdf, 620KB]
Studies of crack dynamics in clay soil. I. Experimental methods, results and morphological quantification: Hans-Jörg Vogel, Heiko Hoffmann, Kurt Roth; Geoderma, Vol. 125, pp. 203-211, 2005; [pdf, 576KB]
Studies of crack dynamics in clay soil. II. A physically based model for crack formation: Hans-Jörg Vogel, Heiko Hoffmann, Andreas Leopold, Kurt Roth; Geoderma, Vol. 125, pp. 213-223, 2005; [pdf, 596KB]
An extension of Neural Gas to local PCA: Ralf Möller, Heiko Hoffmann; Neurocomputing, Vol. 62, pp. 305-326, 2004; [pdf, 1194KB]
Cross-correlation studies with seismic noise: Heiko Hoffmann, John Winterflood, Yong-Jing Cheng, David G. Blair; Classical and Quantum Gravity, Vol. 19, pp. 1709-1716, 2002; [pdf, 152KB]

Peer-reviewed full-length conference articles

Pooling by Sliced-Wasserstein Embedding: Navid Naderializadeh, Joseph F. Comer, Reed W. Andrews, Heiko Hoffmann, and Soheil Kolouri; Conference on Neural Information Processing Systems (NeurIPS), 2021
Wasserstein Embedding for Graph Learning: Soheil Kolouri, Navid Naderializadeh, Gustavo K. Rohde, and Heiko Hoffmann; International Conference on Learning Representations (ICLR), 2021
Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs: Soheil Kolouri, Aniruddha Saha, Hamed Pirsiavash, and Heiko Hoffmann; Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (oral presentation)
Explainability Methods for Graph Convolutional Neural Networks: Phillip Pope, Soheil Kolouri, Mohammad Rostami, Charles E Martin, and Heiko Hoffmann; Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (oral presentation, acceptance rate for orals: 5%); [pdf, 2.2M]
Sliced Wasserstein Distance for Learning Gaussian Mixture Models: Soheil Kolouri, Gustavo K. Rohde, and Heiko Hoffmann; Conference on Computer Vision and Pattern Recognition (CVPR), 2018; [pdf, 4.1M]
Explaining Distributed Neural Activations via Unsupervised Learning: Soheil Kolouri, Charles E Martin, and Heiko Hoffmann; Conference on Computer Vision and Pattern Recognition, Explainable Computer Vision Workshop, 2017 (oral presentation); [pdf, 1.6M]
Fast Re-learning of a Controller from Sparse Data: Charles E Martin and Heiko Hoffmann; IEEE International Conference on Systems, Man, and Cybernetics, 2014 (oral presentation); [pdf, 308K]
Fast pattern matching with time-delay neural networks: Heiko Hoffmann, Michael Howard, and Michael Daily; International Joint Conference on Neural Networks , 2011 (oral presentation); [pdf, 1.3M]
Toward Ultra High Speed Locomotors: Design and Test of a Cheetah Robot Hindlimb: M. Anthony Lewis, Matthew R Bunting, Behnam Salemi, and Heiko Hoffmann; IEEE International Conference on Robotics and Automation , 2011 (oral presentation); [pdf, 1.5M]
Biologically-inspired dynamical systems for movement generation: Automatic real-time goal adaptation and obstacle avoidance: Heiko Hoffmann, Peter Pastor, Dae-Hyung Park, and Stefan Schaal; IEEE International Conference on Robotics and Automation , 2009 (oral presentation); [pdf, 692K]
Learning and Generalization of Motor Skills by Learning from Demonstration: Peter Pastor, Heiko Hoffmann, Tamim Asfour, and Stefan Schaal; IEEE International Conference on Robotics and Automation , 2009 (oral presentation); [pdf, 1548K]
Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields: Dae-Hyung Park, Heiko Hoffmann, Peter Pastor, and Stefan Schaal; IEEE International Conference on Humanoid Robots , 2008 (oral presentation); [pdf, 672K]
Sensor-assisted adaptive motor control under continuously varying context: Heiko Hoffmann, Georgios Petkos, Sebastian Bitzer, and Sethu Vijayakumar; Proc. International Conference on Informatics in Control, Automation, and Robotics; presented at ICINCO, 2007 (oral presentation); [pdf, 1096KB]
Action Selection and Mental Transformation Based on a Chain of Forward Models: Heiko Hoffmann, Ralf Möller; S. Schaal, A. Ijspeert, A. Billard, S. Vijayakumar, J. Hallam, and J.-A. Meyer (Eds.); Proceedings of the 8th Conference on Simulation of Adaptive Behavior (SAB '04), pp. 213-222, MIT Press, 2004 (oral presentation); [pdf, 612KB]
Learning internal models for eye-hand coordination in reaching and grasping: Wolfram Schenck, Heiko Hoffmann, Ralf Möller; F. Schmalhofer, R. M. Young, G. Katz (Eds.); Proc. EuroCogSci, pp. 289-294, Lawrence Erlbaum Associates: Mahwah, New Jersey, 2003 (oral presentation); [pdf, 872KB]
Unsupervised Learning of a Kinematic Arm Model: Heiko Hoffmann, Ralf Möller; O. Kaynak, E. Alpaydin, E. Oja, L. Xu (Eds.); Artificial Neural Networks and Neural Information Processing - ICANN/ICONIP 2003 (oral presentation); LNCS 2714, pp. 463-470, Springer, Heidelberg; [pdf, 158KB]

Peer-reviewed short conference articles

Interactive Audio-Tactile Annotation of 3D Point Clouds for Robotic Manipulation: Jivko Sinapov, Darren Earl, Derek Mitchell, and Heiko Hoffmann; ICRA Mobile Manipulation Workshop on Interactive Perception, 2013; [pdf, 370KB]

Simple finger movements require complex coordination of excursions and forces across all muscles: Jason Kutch, Manish Kurse, Heiko Hoffmann, Evangelos Theodorou, Rod Hentz, Caroline Leclercq, Isabella Fassola, and Francisco Valero-Cuevas; Annual Meeting for the American Society of Biomechanics, State College, Pennsylvania, August 26-29, 2009

Optimization strategies in human reinforcement learning: Heiko Hoffmann, Evangelos Theodorou, and Stefan Schaal; Advances in Computational Motor Control VII, Symposium at the Society for Neuroscience Meeting, Washington DC, 2008; [pdf, 104KB]

Dynamic movement primitives for movement generation motivated by convergent force fields in frog: Heiko Hoffmann, Peter Pastor, and Stefan Schaal; Adaptive Motion of Animals and Machines (AMAM), Cleveland, Ohio, 2008; [pdf, 212KB]

Movement generation by learning from demonstration and generalization to new targets: Peter Pastor, Heiko Hoffmann, and Stefan Schaal; Adaptive Motion of Animals and Machines (AMAM), Cleveland, Ohio, 2008; [pdf, 204KB]

Combining dynamic movement primitives and potential fields for online obstacle avoidance: Dae-Hyung Park, Heiko Hoffmann, and Stefan Schaal; Adaptive Motion of Animals and Machines (AMAM), Cleveland, Ohio, 2008; [pdf, 240KB]

Human movement generation based on convergent flow fields: A computational model and a behavioral experiment: Heiko Hoffmann and Stefan Schaal; Advances in Computational Motor Control VI, Symposium at the Society for Neuroscience Meeting, San Diego, 2007; [pdf, 104KB]

Modellierung der Rissdynamik in tonigen Böden: Andreas Leopold, Heiko Hoffmann, Hans-Jörg Vogel, Kurt Roth; Mitt. Dtsch. Bodenkundl. Ges., Vol. 102, pp. 109-110, 2003

Abstracts

Are reaching movements planned in kinematic or dynamic coordinates?: Alice Ellmer, Heiko Hoffmann, and Stefan Schaal; Neural Control of Movement, Naples, Florida, 2010; [html] [poster]

Error-feedback control through a forward model predicts preferential control of task-relevant parameters as observed in human finger muscle activation: Heiko Hoffmann, Evangelos Theodorou, and Francisco Valero-Cuevas; Society for Neuroscience, Chicago, Il, 2009

Muscle synergies may be artifacts of biomechanics rather than neural constraints, and are not necessary to simplify control: Jason Kutch, Manish Kurse, Heiko Hoffmann, Art Kuo, and Francisco Valero-Cuevas; Society for Neuroscience, Chicago, Il, 2009

Control of muscle strain energy as a robust means to produce slow and accurate finger movements: Proof of concept via hardware and cadaver implementation: Heiko Hoffmann, Jason Kutch, Manish Kurse, and Francisco Valero-Cuevas; Neural Control of Movement, Waikoloa, Hawaii, 2009; [html] [poster]

Human optimization strategies under reward feedback: Heiko Hoffmann, Evangelos Theodorou, and Stefan Schaal; Neural Control of Movement, Waikoloa, Hawaii, 2009; [html] [poster]

Do humans plan continuous trajectories in kinematic coordinates?: Heiko Hoffmann and Stefan Schaal; Society for Neuroscience, Washington, D.C., 2008; [html] [poster]

Behavioral experiments on reinforcement learning in human motor control: Heiko Hoffmann, Evangelos Theodorou, and Stefan Schaal; Neural Control of Movement, Naples, Florida, 2008; [html]

The dual role of uncertainty in force field learning: Michael Mistry, Evangelos Theodorou, Heiko Hoffmann, and Stefan Schaal; Neural Control of Movement, Naples, Florida, 2008; [html]

A computational model of human trajectory planning based on convergent flow fields: Heiko Hoffmann and Stefan Schaal; Society for Neuroscience, San Diego, California, 2007; [html]

A computational model of arm trajectory modification using dynamic movement primitives: Peyman Mohajerian, Heiko Hoffmann, Michael Mistry, and Stefan Schaal; Society for Neuroscience, San Diego, California, 2007

Uncertain 3D force fields in reaching movements: Do humans favor robust or average performance?: Michael Mistry, Evangelos Theodorou, Heiko Hoffmann, and Stefan Schaal; Society for Neuroscience, San Diego, California, 2007

Invited articles

SAR automatic target recognition with less labels: Joseph F. Comer, Reed W. Andrews, Navid Naderializadeh, Soheil Kolouri, and Heiko Hoffmann; Proc. SPIE 11394, Automatic Target Recognition XXX, 113940Q, 24 April 2020

Rapid 3D registration using local subtree caching in Iterative Closest Point (ICP) algorithm: Ryan Uhlenbrock, Kyungnam Kim, Heiko Hoffmann, and Jean J. Dolne; SPIE Optics and Photonics, Unconventional and Indirect Imaging, Image Reconstruction, and Wavefront Sensing, 2017

Classification and segmentation of orbital space-based objects against terrestrial distractors for the purpose of finding holes in Shape from Motion 3D reconstruction: T. Nathan Mundhenk, Arturo Flores, and Heiko Hoffmann; SPIE Electronic Imaging, 2014; [pdf, 8.9M]

Biologically-inspired image processing for machine grasping: Heiko Hoffmann; The Neuromorphic Engineer, Vol. 2, Issue 2, 2005, p. 7; [html]

Letters

Failure-based resource allocation is insufficient to prevent future catastrophic blackouts: Heiko Hoffmann and David W. Payton; Science, eLetter in response to Small vulnerable sets determine large network cascades in power grids, Vol. 358, Issue 6365, eaan3184, 2017.; Feb 1, 2018

Books

Unsupervised Learning of Visuomotor Associations: Heiko Hoffmann; MPI Series in Biological Cybernetics, Vol. 11, 2005, Logos Verlag Berlin; ISBN 3-8325-0858-9; PhD thesis, Faculty of Technology, Bielefeld University; [pdf, 7800KB] [html]

Patents (granted)

Method and system for machine vision detection: Heiko Hoffmann; US patent 11151405, Oct 19, 2021

System and method for estimating uncertainty of the decisions made by a supervised machine learner: Soheil Kolouri and Heiko Hoffmann; US patent 11086299, Aug 10, 2021

Machine-vision method to classify input data based on object components: Soheil Kolouri, Charles E Martin, Heiko Hoffmann; US patent 11023789, Jun 1, 2021

Process to control a networked system of time varying devices: Byron Heersink, Michael A Warren, and Heiko Hoffmann; US patent 10926776, Feb 23, 2021

System for co-adaptation of robot control to human biomechanics: Vincent DeSapio and Heiko Hoffmann; US patent 10899017, Jan 26, 2021

Method and System for Detecting Change of Context in Video Streams: Charles E Martin, Nigel D Stepp, Soheil Kolouri, and Heiko Hoffmann; US patent 10878276, Dec 29, 2020

Three-dimensional point data alignment with pre-alignment: Kyungnam Kim and Heiko Hoffmann; US patent 10825259, Nov 3, 2020

Method for understanding machine-learning decisions based on camera data: Charles E Martin, Soheil Kolouri, and Heiko Hoffmann; US patent 10803356, Oct 13, 2020

Machine-vision system for discriminant localization of objects: Soheil Kolouri, Charles E Martin, and Heiko Hoffmann; US patent 10691972, Jun 23, 2020

Process to reduce the probability of large cascading failures in a transmission network: Heiko Hoffmann and Tsai-Ching Lu; US patent 10691154, Jun 23, 2020

System and method for detecting moving obstacles based on sensory prediction from ego-motion: Ken Kim, Hyukseong Kwon, Heiko Hoffmann; US patent 10679355, Jun 9, 2020

Machine vision system for recognizing novel objects: Soheil Kolouri, Charles E Martin, Ken Kim, and Heiko Hoffmann; US patent 10607111, Mar 31, 2020

System and method for self-organized critical image segmentation: Heiko Hoffmann and David W. Payton; US patent 10580142, Mar 3, 2020

Autonomous performance of an operation on an object using a generated dense 3D model of the object: Hyukseong Kwon, Kyungnam Kim, and Heiko Hoffmann; US patent 10574967, Feb 25, 2020

System and method for classifying agents based on agent movement patterns: Terrell N. Mundhenk and Heiko Hoffmann; US patent 10514694, Dec 24, 2019

Device and method to decode volitional motor commands using a biomechanical model for controlling a prosthetic limb: Vincent DeSapio, Darren Earl, and Heiko Hoffmann; US patent 10507121, Dec 17, 2019

Method and apparatus to determine optimal brain stimulation to induce desired behavior: Praveen K Pilly, Michael D Howard, Heiko Hoffmann, Tsai-Ching Lu, Kang-Yu Ni, and David W Payton; US patent 10420937, Sep 24, 2019

Robust recognition on degraded imagery by exploiting known image transformation under motion: Heiko Hoffmann and Ken Kim; US patent 10332265, Jun 25, 2019

Method and system for identifying wire contact insertion holes of a connector: Heiko Hoffmann; US patent 10288410, May 14, 2019

Device and method to detect attacks on mobile ad hoc networks based on network flux: Heiko Hoffmann and Gavin D. Holland; US patent 10187404, Jan 22, 2019

Device and method to automatically tune the nerve stimulation pattern of a sensory feedback capable prosthesis: Heiko Hoffmann, Jaehoon Choe, and Corey Thibeault; US patent 10166394, Jan 1, 2019

Method to suppress cascading failures in a transmission network: Heiko Hoffmann and David W. Payton; US patent 10139844, Nov 28, 2018

Neural network device with engineered delays for pattern storage and matching (divisional): Heiko Hoffmann; US patent 10095976, Oct 9, 2018

System and method for assistive gait intervention and fall prevention: Vincent DeSapio, Michael D. Howard, Matthew E. Phillips, Kevin R. Martin, Heiko Hoffmann, and David W. Payton; US patent 10052062, Aug 21, 2018

Adaptive control system capable of recovering from unexpected situations: Heiko Hoffmann and David W. Payton; US patent 10001760, Jun 19, 2018

System and method for robot supervisory control with an augmented reality user interface: Heiko Hoffmann and Michael J. Daily; US patent 9880553, Jan 30, 2018

Device and method for merging 3D point clouds from sparsely distributed viewpoints: Darren J. Earl, Ryan M. Uhlenbrock, and Heiko Hoffmann; US patent 9858640, Jan 2, 2018

Method for tele-robotic operations over time-delayed communication links: Heiko Hoffmann, David W Payton, and Vincent DeSapio; US patent 9776325, Oct 3, 2017

System and method for controller adaptation: Charles E. Martin and Heiko Hoffmann; US patent 9747543, Aug 29, 2017

Method for calibrating an articulated end effector employing a remote digital camera: Ryan M. Uhlenbrock and Heiko Hoffmann; US patent 9616569, Apr 11, 2017

Robotic control device and method for manipulating a hand-held tool: Heiko Hoffmann and Behnam Salemi; US patent 9613180, Apr 4, 2017

Self-stabilizing system for multiple interacting controllers: Heiko Hoffmann and David W Payton; US patent 9557722, Jan 31, 2017

Method for classification and segmentation and forming 3D models from images: Terrell N. Mundhenk, Arturo Flores, and Heiko Hoffmann; US patent 9530218, Dec 27, 2016

System and method for quick scripting of tasks for autonomous robotic manipulation: Darren Earl, Derek Mitchell, and Heiko Hoffmann; US patent 9486918, Nov 8, 2016

Dynamic obstacle avoidance in a robotic system: Derek Mitchell and Heiko Hoffmann; US patent 9403275, Aug 2, 2016

Dynamical system-based robot velocity control: Heiko Hoffmann, David W. Payton, and Derek Mitchell; US patent 9381643, Jul 5, 2016

A system for controlling motion and constraint forces in a robotic system without the need for force sensing: Vincent DeSapio and Heiko Hoffmann; US patent 9364951, Jun 14, 2016

System and method for deep packet inspection and intrusion detection: Heiko Hoffmann, Michael J Daily, Gavin D Holland, Karim El Defrawy; US patent 9336239, May 10, 2016

Neural network device with engineered delays for pattern storage and matching (divisional): Heiko Hoffmann; US patent 9311595, Apr 12, 2016

Device and method to localize and control a tool tip with a robot arm: Zhichao Chen and Heiko Hoffmann; US patent 9259840, Feb 16, 2016

System and Method for Fast Template Matching in 3D: Heiko Hoffmann, Hooman Kazemi, and Michael J Daily; US patent 9171247, Oct 27, 2015

Device and method to identify functional parts of tools for robotic manipulation: Jivko Sinapov and Heiko Hoffmann; US patent 9144905, Sep 29, 2015

Secure Pattern Matching: Karim El Defrawy, Kirill Minkovich, Joshua W. Baron, Eric P. Tressler, and Heiko Hoffmann; US patent 9009089, Apr 14, 2015

Robotic visual perception system: Suhas E Chelian, Rashmi N Sundareswara, and Heiko Hoffmann; US patent 9002098, Apr 7, 2015

Neural network device with engineered delays for pattern storage and matching: Heiko Hoffmann; US patent 8818923, Aug 26, 2014

Patents (pending)

System and method for automatic target recognition from SAR images with less labels: Joseph Comer, Navid Naderializadeh, Reed Andrews, Soheil Kolouri, and Heiko Hoffmann; US patent pending, filed 2021

Process to make machine object detection robust to adversarial attacks: Soheil Kolouri, David W. Payton, and Heiko Hoffmann; US patent pending, filed 2021

Image-based guidance for robotic wire pickup: Heiko Hoffmann, Jeffrey A. McCaskey, Lars E. Blacken, Damien O. Martin, and Bradley J. Mitchell; US patent pending, filed 2021

Process to learn new image classes without labels: Heiko Hoffmann and Soheil Kolouri; US patent pending, filed 2020

Method and system for error correction in automated wire contact insertion within a connector: Heiko Hoffmann; US patent pending, filed 2020

Learning actions with few labels in the embedded space: Amir Rahimi, Hyukseong Kwon, Amit Agarwal, Soheil Kolouri, and Heiko Hoffmann; US patent pending, filed 2020

Action classification using deep embedded clustering: Amir Rahimi, Hyukseong Kwon, Amit Agarwal, and Heiko Hoffmann; US patent pending, filed 2020

System and method for detecting backdoor/Trojan attacks in convolutional neural networks: Soheil Kolouri and Heiko Hoffmann; US patent pending, filed 2020

Method and system for alignment of wire contact with wire contact insertion holes of a connector: Heiko Hoffmann; US patent pending, filed 2019

Method and system for alignment and insertion of wire contact with wire contact insertion holes of a connector: Alexander Graber-Tilton, Richard Patrick, and Heiko Hoffmann; US patent pending, filed 2019

Sparse Associative Memory for Identification of Objects: Heiko Hoffmann; US patent pending, filed 2019

System and method for classifying agents based on their movement patterns (divisional): Terrell N. Mundhenk and Heiko Hoffmann; US patent pending, filed 2019

Method for discovering chemically active compounds of a molecule: Soheil Kolouri, Mohammad Rostami, Charles E Martin, and Heiko Hoffmann; US patent pending, filed 2019

System for opportunistic health assessment on smartphones: Vincent DeSapio, Jaehoon Choe, Iman Mohammadrezazadeh, Kang-Yu Ni, Heiko Hoffmann, Charles E Martin, and Yuri Owechko; US patent pending, filed 2019

System and method for audio classification based on unsupervised attribute learning: Charles E Martin, Soheil Kolouri, and Heiko Hoffmann; US patent pending, filed 2018

Self-organized-critical pattern generation to solve high-dimensional optimization problems: Heiko Hoffmann and David W. Payton; US patent pending, filed 2015