Holographic Graph Neuron: A Bioinspired Architecture for Pattern Processing

Kleyko, Denis; Osipov, Evgeny; Senior, Alexander; Khan, Asad I.; Şekercioğlu, Y. Ahmet

doi:10.1109/tnnls.2016.2535338

Cited by 63 publications

(29 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the use of these MAP operations, an encoder can be designed for various tasks, e.g., EMG [20], [22], [49], EEG [23], [50], ECoG [51], ExG [45], or in general pattern processing [52]. The encoder emits a hypervector representing the event of interest that is then fed into an associative memory (AM) for training and inference.…”

Section: B Hyperdimensional Computingmentioning

confidence: 99%

Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform Using Hyperdimensional Computing

Benatti

Montagna

Kartsch

et al. 2019

IEEE Trans. Biomed. Circuits Syst.

View full text Add to dashboard Cite

This work presents a wearable EMG gesture recognition system based on the hyperdimensional (HD) computing paradigm, running on a programmable Parallel Ultra-Low-Power (PULP) platform. The processing chain includes efficient on-chip training, which leads to a fully embedded implementation with no need to perform any offline training on a personal computer. The proposed solution has been tested on 10 subjects in a typical gesture recognition scenario achieving 85% average accuracy on 11 gestures recognition, which is aligned with the State-Of-the-Art (SoA), with the unique capability of performing online learning. Furthermore, by virtue of the Hardware (HW) friendly algorithm and of the efficient PULP System-on-Chip (SoC) (Mr. Wolf) used for prototyping and evaluation, the energy budget required to run the learning part with 11 gestures is 10.04mJ, and 83.2µJ per classification. The system works with a average power consumption of 10.4mW in classification, ensuring around 29h of autonomy with a 100mAh battery. Finally, the scalability of the system is explored by increasing the number of channels (up-to 256 electrodes), demonstrating the suitability of our approach as universal, energy-efficient biopotential wearable recognition framework.

show abstract

Section: B Hyperdimensional Computingmentioning

confidence: 99%

Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform Using Hyperdimensional Computing

Benatti

Montagna

Kartsch

et al. 2019

IEEE Trans. Biomed. Circuits Syst.

View full text Add to dashboard Cite

show abstract

“…In [90], the formation of sparse memory vectors (with an additional operation of context-dependent thinning [134]) is considered, and in [91] the probability of correct recognition is estimated. The use of graded connections (the formation of the memory vector is done by addition), including subsequent binarization, and the classification problem for vectors not from the base, are considered in [89,91].…”

Section: The Generalization Of Krotov-hopfieldmentioning

confidence: 99%

Neural Autoassociative Memories for Binary Vectors: A Survey

Gritsenko¹,

Rachkovskij²,

Frolov³

et al. 2017

Kibern. vyčisl. teh.

View full text Add to dashboard Cite

Introduction. Neural network models of autoassociative, distributed memory allow storage and retrieval of many items (vectors) where the number of stored items can exceed the vector dimension (the number of neurons in the network). This opens the possibility of a sublinear time search (in the number of stored items) for approximate nearest neighbors among vectors of high dimension.The purpose of this paper is to review models of autoassociative, distributed memory that can be naturally implemented by neural networks (mainly with local learning rules and iterative dynamics based on information locally available to neurons).Scope. The survey is focused mainly on the networks of Hopfield, Willshaw and Potts, that have connections between pairs of neurons and operate on sparse binary vectors. We discuss not only autoassociative memory, but also the generalization properties of these networks. We also consider neural networks with higher-order connections and networks with a bipartite graph structure for non-binary data with linear constraints.Conclusions. In conclusion we discuss the relations to similarity search, advantages and drawbacks of these techniques, and topics for further research. An interesting and still not completely resolved question is whether neural autoassociative memories can search for approximate nearest neighbors faster than other index structures for similarity search, in particular for the case of very high dimensional vectors. Introduction. Neural network models of autoassociative, distributed memory allow storage and retrieval of many items (vectors) where the number of stored items can exceed the vector dimension (the number of neurons in the network). This opens the possibility of a sublinear time search (in the number of stored items) for approximate nearest neighbors among vectors of high dimension.The purpose of this paper is to review models of autoassociative, distributed memory that can be naturally implemented by neural networks (mainly with local learning rules and iterative dynamics based on information locally available to neurons).Scope. The survey is focused mainly on the networks of Hopfield, Willshaw and Potts, that have connections between pairs of neurons and operate on sparse binary vectors. We (Online), ISSN 0454-9910 (Print). Киб. и выч. техн. 2017. № 2 (188) 6 discuss not only autoassociative memory, but also the generalization properties of these networks. We also consider neural networks with higher-order connections and networks with a bipartite graph structure for non-binary data with linear constraints.Conclusions. In conclusion we discuss the relations to similarity search, advantages and drawbacks of these techniques, and topics for further research. An interesting and still not completely resolved question is whether neural autoassociative memories can search for approximate nearest neighbors faster than other index structures for similarity search, in particular for the case of very high dimensional vectors. ISSN 2519-2205 (Online), ISSN 0454-9910 (Print). Киб...

show abstract

“…Note that such data representation schemes by similarity preserving binary vectors have been developed for objects represented by various data types, mainly for (feature) vectors (see survey in [131]), but also for structured data types such as sequences [102,72,85,86] and graphs [127,128,148,136,62,134]. A significant part of this research is developed in the framework of distributed representations [45,76,106,126,89], including binary sparse distributed representations [102,98,103,127,128,113,114,137,138,139,148,135,136,61,134,129,130,131,132,31,33] and dense distributed representations [75,76] (see [82,84,87,88,83] for examples of their applications).…”

Section: Generalization In Namsmentioning

confidence: 99%

Untitled

2017

Kibern. vyčisl. teh.

View full text Add to dashboard Cite

show abstract

Holographic Graph Neuron: A Bioinspired Architecture for Pattern Processing

Cited by 63 publications

References 29 publications

Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform Using Hyperdimensional Computing

Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform Using Hyperdimensional Computing

Neural Autoassociative Memories for Binary Vectors: A Survey

Untitled

Contact Info

Product

Resources

About