An Introduction to Hyperdimensional Computing for Robotics

Hyperdimensional computing combines very high-dimensional vector spaces (e.g. 10,000 dimensional) with a set of carefully designed operators to perform symbolic computations with large numerical vectors. The goal is to exploit their representational power and noise robustness for a broad range of computational tasks. Although there are surprising and impressive results in the literature, the application to practical problems in the area of robotics is so far very limited. In this work, we aim at providing an easy to access introduction to the underlying mathematical concepts and describe the existing computational implementations in form of vector symbolic architectures (VSAs). This is accompanied by references to existing applications of VSAs in the literature. To bridge the gap to practical applications, we describe and experimentally demonstrate the application of VSAs to three different robotic tasks: viewpoint invariant object recognition, place recognition and learning of simple reactive behaviors. The paper closes with a discussion of current limitations and open questions.

[1]  Trevor Cohen,et al.  Reasoning with vectors: A continuous model for fast robust inference , 2015, Log. J. IGPL.

[2]  Jonathan Goldstein,et al.  When Is ''Nearest Neighbor'' Meaningful? , 1999, ICDT.

[3]  Niko Sünderhauf,et al.  On the performance of ConvNet features for place recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Evgeny Osipov,et al.  Imitation of honey bees’ concept learning processes using Vector Symbolic Architectures , 2015, BICA 2015.

[5]  Wolfram Burgard,et al.  The limits and potentials of deep learning for robotics , 2018, Int. J. Robotics Res..

[6]  Alexander Legalov,et al.  Associative synthesis of finite state automata model of a controlled object with hyperdimensional computing , 2017, IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society.

[7]  Aditya Joshi,et al.  Language Geometry Using Random Indexing , 2016, QI.

[8]  Pentti Kanerva,et al.  Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors , 2009, Cognitive Computation.

[9]  Geoffrey E. Hinton.  Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1991 .

[10]  Subutai Ahmad,et al.  Properties of Sparse Distributed Representations and their Application to Hierarchical Temporal Memory , 2015, ArXiv.

[11]  Alex Graves,et al.  Associative Long Short-Term Memory , 2016, ICML.

[12]  Jan M. Rabaey,et al.  Classification and Recall With Binary Hyperdimensional Computing: Tradeoffs in Choice of Density and Mapping Characteristics , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Subutai Ahmad,et al.  Why Neurons Have Thousands of Synapses, a Theory of Sequence Memory in Neocortex , 2015, Front. Neural Circuits.

[14]  J. Franklin,et al.  The elements of statistical learning: data mining, inference and prediction , 2005 .

[15]  Peter Protzel,et al.  Learning Vector Symbolic Architectures for Reactive Robot Behaviours , 2017 .

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Geoffrey E. Hinton,et al.  Distributed representations and nested compositional structure , 1994 .

[18]  Friedrich T. Sommer,et al.  A Theory of Sequence Indexing and Working Memory in Recurrent Neural Networks , 2018, Neural Computation.

[19]  Jan M. Rabaey,et al.  High-Dimensional Computing as a Nanoscalable Paradigm , 2017, IEEE Transactions on Circuits and Systems I: Regular Papers.

[20]  Peer Neubert,et al.  Local region detector + CNN based landmarks for practical place recognition in changing environments , 2015, 2015 European Conference on Mobile Robots (ECMR).

[21]  R. Jackendoff.  Foundations of Language: Brain, Meaning, Grammar, Evolution , 2002 .

[22]  Suraj Bajracharya,et al.  Learning Behavior Hierarchies via High-Dimensional Sensor Projection , 2013, AAAI Workshop: Learning Rich Representations from Low-Level Sensors.

[23]  Richard Bellman,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[24]  Charu C. Aggarwal,et al.  On the Surprising Behavior of Distance Metrics in High Dimensional Spaces , 2001, ICDT.

[25]  Gordon Wyeth,et al.  SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights , 2012, 2012 IEEE International Conference on Robotics and Automation.

[26]  Wolfram Burgard,et al.  Probabilistic Robotics (Intelligent Robotics and Autonomous Agents) , 2005 .

[27]  Z. Harris,et al.  Foundations of language , 1941 .

[28]  Nikolaos Papakonstantinou,et al.  Fault detection in the hyperspace: Towards intelligent automation systems , 2015, 2015 IEEE 13th International Conference on Industrial Informatics (INDIN).

[29]  Scott Purdy.  Encoding Data for HTM Systems , 2016, ArXiv.

[30]  Arnold W. M. Smeulders,et al.  The Amsterdam Library of Object Images , 2004, International Journal of Computer Vision.

[31]  Pentti Kanerva,et al.  Fully Distributed Representation , 1997 .

[32]  Ross W. Gayler.  Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience , 2004, ArXiv.

[33]  Niko Sünderhauf,et al.  Are We There Yet? Challenging SeqSLAM on a 3000 km Journey Across All Four Seasons , 2013 .

[34]  Subutai Ahmad,et al.  A Sequence-Based Neuronal Model for Mobile Robot Localization , 2018, KI.

[35]  Trevor Bekolay,et al.  A Large-Scale Model of the Functioning Brain , 2012, Science.

[36]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[37]  Ross W. Gayler,et al.  Multiplicative Binding, Representation Operators & Analogy , 1998 .

[38]  Dmitri A. Rachkovskij,et al.  SIMILARITY‐BASED RETRIEVAL WITH STRUCTURE‐SENSITIVE SPARSE BINARY DISTRIBUTED REPRESENTATIONS , 2012, Comput. Intell..

[39]  Pentti Kanerva.  Computing with 10,000-bit words , 2014, 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton).