Sparse distributed memory for experience-based robot manipulation

Jockel, Sascha; Lindner, Felix; Zhang, Jianwei

doi:10.1109/robio.2009.4913187

Cited by 7 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This stands in contrast to models that use localist representations , e.g., all published versions of the HMAX family of models, (e.g., Murray and Kreutz-Delgado, 2007 ; Serre et al, 2007 ) and other cortically-inspired hierarchical models (Kouh and Poggio, 2008 ; Litvak and Ullman, 2009 ; Jitsev, 2010 ) and the majority of graphical probability-based models (e.g., hidden Markov models, Bayesian nets, dynamic Bayesian nets). There are several other models for which SDC is central, e.g., SDM (Kanerva, 1988 , 1994 , 2009 ; Jockel, 2009 ), Convergence-Zone Memory (Moll and Miikkulainen, 1997 ), Associative-Projective Neural Networks (Rachkovskij, 2001 ; Rachkovskij and Kussul, 2001 ), Cogent Confabulation (Hecht-Nielsen, 2005 ), Valiant's “positive shared” representations (Valiant, 2006 ; Feldman and Valiant, 2009 ), and Numenta's Grok (described in Numenta white papers). However, none of these models has been substantially elaborated or demonstrated in an explicitly hierarchical architecture and most have not been substantially elaborated for the spatiotemporal case.…”

Section: Overall Model Conceptmentioning

confidence: 99%

Sparseyâ„¢: event recognition via deep hierarchical sparse distributed codes

Rinkus¹

2014

Front. Comput. Neurosci.

View full text Add to dashboard Cite

The visual cortex's hierarchical, multi-level organization is captured in many biologically inspired computational vision models, the general idea being that progressively larger scale (spatially/temporally) and more complex visual features are represented in progressively higher areas. However, most earlier models use localist representations (codes) in each representational field (which we equate with the cortical macrocolumn, “mac”), at each level. In localism, each represented feature/concept/event (hereinafter “item”) is coded by a single unit. The model we describe, Sparsey, is hierarchical as well but crucially, it uses sparse distributed coding (SDC) in every mac in all levels. In SDC, each represented item is coded by a small subset of the mac's units. The SDCs of different items can overlap and the size of overlap between items can be used to represent their similarity. The difference between localism and SDC is crucial because SDC allows the two essential operations of associative memory, storing a new item and retrieving the best-matching stored item, to be done in fixed time for the life of the model. Since the model's core algorithm, which does both storage and retrieval (inference), makes a single pass over all macs on each time step, the overall model's storage/retrieval operation is also fixed-time, a criterion we consider essential for scalability to the huge (“Big Data”) problems. A 2010 paper described a nonhierarchical version of this model in the context of purely spatial pattern processing. Here, we elaborate a fully hierarchical model (arbitrary numbers of levels and macs per level), describing novel model principles like progressive critical periods, dynamic modulation of principal cells' activation functions based on a mac-level familiarity measure, representation of multiple simultaneously active hypotheses, a novel method of time warp invariant recognition, and we report results showing learning/recognition of spatiotemporal patterns.

show abstract

Section: Overall Model Conceptmentioning

confidence: 99%

Sparseyâ„¢: event recognition via deep hierarchical sparse distributed codes

Rinkus¹

2014

Front. Comput. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Other characteristics of the SDMs are also significant, such as high tolerance to noise [14], [15], robustness to failure of individual locations and graceful degradation, one-shot learning, suitability to work with sequences [1], [16] and phenomena typical of human memory, such as knowing that one knows or tip of the tongue. Detailed descriptions and demonstrations of the mathematical properties of the memory can be found in [1] and [17], [18]. Figure 1 shows a model of an SDM.…”

Section: Sparse Distributed Memoriesmentioning

confidence: 99%

Robot navigation and manipulation based on a predictive associative memory

Jockel¹,

Mendes

Zhang³

et al. 2009

2009 IEEE 8th International Conference on Development and Learning

View full text Add to dashboard Cite

Abstract-Proposed in the 1980s, the Sparse Distributed Memory (SDM) is a model of an associative memory based on the properties of a high dimensional binary space. This model has received some attention from researchers of different areas and has been improved over time. However, a few problems have to be solved when using it in practice, due to the non-randomness characteristics of the actual data. We tested an SDM using different forms of encoding the information, and in two different domains: robot navigation and manipulation. Our results show that the performance of the SDM in the two domains is affected by the way the information is actually encoded, and may be improved by some small changes in the model.

show abstract

“…It is the subjective experience memory of the agent's environmental information, and it is the basis for positioning and navigation. Inspired by the navigation capabilities of mammals (such as rats), research on how mammals conduct map construction, positioning and navigation has gained great interest in the field of robotics [5] [6] [7]. Compared with robots, mammals can adapt to complex environments and tasks well, study knowledge, and retrieval previous ex-periences to complete new work.…”

Section: Introductionmentioning

confidence: 99%

Method of Robot Episode Cognition Based on Hippocampus Mechanism

et al. 2022

View full text Add to dashboard Cite

This paper proposes a method to realize the robot's self-learning of unknown environment by using a episode cognitive model inspired by the hippocampus. The episode cognitive map constructed through self-learning is suitable for robot navigation in an unknown environment. Which solve the problem of robustness of the robot's perception in complex and dynamic environments. The model we propose is called the hippocampus episode cognitive network (HEC), which is based on the physiological functions of the hippocampus CA1, CA3 and the dentate gyrus combined with the adaptive resonance theory (ART) network. Extract new events through the incremental generation of cognitive neurons, and encode the events into episode through spatio-temporal connections. The episode nodes can be connected to generate a episode cognitive map. This method can realize learning, storage, and update information for autonomous mobility robots in unknown environment. On the basis of the episode cognitive map, the path trajectory can be predicted through the playback of the episode neuron. The experimental results on the mobile robot show that this method can effectively improve the robot's adaptability for positioning and mapping in a complex and dynamic environment.

show abstract

Sparse distributed memory for experience-based robot manipulation

Cited by 7 publications

References 20 publications

Sparseyâ„¢: event recognition via deep hierarchical sparse distributed codes

Sparseyâ„¢: event recognition via deep hierarchical sparse distributed codes

Robot navigation and manipulation based on a predictive associative memory

Method of Robot Episode Cognition Based on Hippocampus Mechanism

Contact Info

Product

Resources

About