检索结果-内蒙古大学图书馆

7th International Conference on Machine Learning Technologies (ICMLT)

作者： Vdovychenko, Ruslan Tulchinsky, Vadim Natl Acad Sci Ukraine VM Glushkov Inst Cybernet Kiev Ukraine

ISBN: (纸本)9781450395748

sparse distributed memory (SDM) and Binary distributed Representations (BDR), as two phenomenological approaches to biological memory modelling, have a lot of common features. The idea of their integration in a hybrid semantic storage model with SDM used as the low (brain cell) level cleaning memory for BDR used as the high-level symbolic information coder seems natural. The hybrid semantic storage must be able to memorize holistic data (like the structures of interconnected and serialized key-value pairs) in a neural network. It has been proposed several times since 1990(th). However, the earlier proposed models are not practical because of insufficient scalability and/or low storage density. The gap between SDM and BDR can be filled using the results of a 3(rd) theory dealing with sparse signals: Compressive Sensing or Sampling (CS). Such a hybrid semantic storage model is presented. We call it CS-SDM to reflect using a new CS-based SDM design as the cleaning memory for a Binary sparse distributed Representation (BSDR) of the holistic data. CS-SDM has been implemented on GPU and demonstrated much better capacity and denoising capabilities than classical SDM designs.

关键词： sparse distributed memory Compressive Sensing Compressive Sampling Binary sparse distributed Representations Vector Symbolic Architecture associative memory neural networks GPU

来源：评论

学校读者我要写书评

暂无评论

In-memory Computing Architectures for sparse distributed memory

引用

IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2016年第4期10卷 855-863页

作者： Kang, Mingu Shanbhag, Naresh R. Univ Illinois Coordinated Sci Lab Urbana IL 61801 USA

This paper presents an energy-efficient and high-throughput architecture for sparse distributed memory (SDM)-a computational model of the human brain [1]. The proposed SDM architecture is based on the recently proposed in-memory computing kernel for machine learning applications called Compute memory (CM) [2], [3]. CM achieves energy and throughput efficiencies by deeply embedding computation into the memory array. SDM-specific techniques such as hierarchical binary decision (HBD) are employed to reduce the delay and energy further. The CM-based SDM (CM-SDM) is a mixed-signal circuit, and hence circuit-aware behavioral, energy, and delay models in a 65 nm CMOS process are developed in order to predict system performance of SDM architectures in the auto- and hetero-associative modes. The delay and energy models indicate that CM-SDM, in general, can achieve up to 25 x and 12 x delay and energy reduction, respectively, over conventional SDM. When classifying 16 x16 binary images with high noise levels (input bad pixel ratios: 15%-25%) into nine classes, all SDM architectures are able to generate output bad pixel ratios (B-o) <= 2%. The CM-SDM exhibits negligible loss in accuracy, i.e., its B-o degradation is within 0.4% as compared to that of the conventional SDM.

关键词： Associative memory brain-inspired computing Compute memory machine learning pattern recognition sparse distributed memory

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and High Throughput sparse distributed memory Architecture

Energy-efficient and High Throughput Sparse Distributed Memo...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Kang, Mingu Kim, Eric P. Keel, Min-sun Shanbhag, Naresh R. Univ Illinois Dept Elect & Comp Engn 1406 W Green St Urbana IL 61801 USA

ISBN: (纸本)9781479983919

This paper presents an energy-efficient VLSI implementation of sparse distributed memory (SDM). High throughput and energy-efficient Hamming distance-based address decoder (CM-DEC) is proposed by employing compute memory [1], where computation is deeply embedded into a memory (SRAM). Hierarchical binary decision (HBD) is also proposed to enhance area- and energy-efficiency of read operation by minimizing data transfer. The SDM is employed as an auto-associative memory with four read iterations and 16 x 16 binary noisy input image with input error rates of 15%, 25%, and 30%. The proposed SDM achieves 39x smaller energy delay product with 14.5x and 2.7x reduced delay and energy, respectively as compared to conventional digital implementation of SDM in 45 nm SOI CMOS process with output error rate degradation less than 0.4%.

关键词： Associative memory Compute memory Machine learning Pattern recognition sparse distributed memory

来源：评论

学校读者我要写书评

暂无评论

Analogical Mapping with sparse distributed memory: A Simple Model that Learns to Generalize from Examples

引用

COGNITIVE COMPUTATION 2014年第1期6卷 74-88页

作者： Emruli, Blerim Sandin, Fredrik Lulea Univ Technol EISLAB S-97187 Lulea Sweden

We present a computational model for the analogical mapping of compositional structures that combines two existing ideas known as holistic mapping vectors and sparse distributed memory. The model enables integration of structural and semantic constraints when learning mappings of the type and computing analogies for novel inputs x (j) . The model has a one-shot learning process, is randomly initialized, and has three exogenous parameters: the dimensionality of representations, the memory size S, and the probability chi for activation of the memory. After learning three examples, the model generalizes correctly to novel examples. We find minima in the probability of generalization error for certain values of chi, S, and the number of different mapping examples learned. These results indicate that the optimal size of the memory scales with the number of different mapping examples learned and that the sparseness of the memory is important. The optimal dimensionality of binary representations is of the order 10(4), which is consistent with a known analytical estimate and the synapse count for most cortical neurons. We demonstrate that the model can learn analogical mappings of generic two-place relationships, and we calculate the error probabilities for recall and generalization.

关键词： Analogical mapping Compositional structures distributed representations Holistic processing sparse distributed memory

来源：评论

学校读者我要写书评

暂无评论

Integer sparse distributed memory: Analysis and results

引用

NEURAL NETWORKS 2013年 46卷 144-153页

作者： Snaider, Javier Franklin, Stan Strain, Steve George, E. Olusegun Univ Memphis Dept Comp Sci Memphis TN 38152 USA Univ Memphis Inst Intelligent Syst Memphis TN 38152 USA Univ Memphis Dept Biomed Engn Memphis TN 38152 USA Univ Memphis Dept Math Sci Memphis TN 38152 USA

sparse distributed memory is an auto-associative memory system that stores high dimensional Boolean vectors. Here we present an extension of the original SDM, the Integer SDM that uses modular arithmetic integer vectors rather than binary vectors. This extension preserves many of the desirable properties of the original SDM: auto-associativity, content addressability, distributed storage, and robustness over noisy inputs. In addition, it improves the representation capabilities of the memory and is more robust over normalization. It can also be extended to support forgetting and reliable sequence storage. We performed several simulations that test the noise robustness property and capacity of the memory. Theoretical analyses of the memory's fidelity and capacity are also presented. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： sparse distributed memory High dimensional space Auto-associative memory

来源：评论

学校读者我要写书评

暂无评论

SDM-Go: an Agent for Go with an Improved Search Process Based on Monte-Carlo Tree Search and sparse distributed memory

SDM-Go: an Agent for Go with an Improved Search Process Base...

引用

IEEE 16th International Conference on Computational Science and Engineering (CSE)

作者： Aguiar, Matheus Araujo Silva Julia, Rita Maria Univ Fed Uberlandia Dept Comp Sci BR-38400 Uberlandia MG Brazil

ISBN: (纸本)9781479948970

This paper describes the player agent for Go named SDM-Go. It uses sparse distributed memory (SDM) as an additional resource to improve the classical Monte-Carlo (MC) simulation based search used by many current top player agents. In this process, the search tree used to select the best move is constructed according to the values of the game boards. The SDM-Go is built upon the Fuego framework. The contributions here are: the use of a SDM to reduce the number of MC simulations and to increase the accuracy of the calculus of the values corresponding to the game boards (nodes) that keep a certain level of similarity with some node of the SDM;the implementation of a bit based representation for the game boards such as not to compromise the performance of the system when checking the similarities among them and;to extend the use of the results of the simulations to update the values of the nodes of the SDM. The use of the SDM represents an approach independent of domain, what reduces the supervised character of the traditional MC simulations. The results obtained in tournaments against the well known open-source agent Fuego confirm the benefits provided by this approach.

关键词： Game Agent for Go sparse distributed memory Monte Carlo Tree Search Simulations

来源：评论

学校读者我要写书评

暂无评论

Volume Signaling and Neural-Indexing by Nitric Oxide in Artificial Neural Networks

引用

IEEE ACCESS 2022年 10卷 82246-82258页

作者： Fernandez-Lopez, Pablo Garcia-Baez, Patricio Cabrera-Leon, Ylermi Navarro-Mesa, Juan L. Suarez-Araujo, Carmen Paz Univ Las Palmas Gran Canaria Inst Cybernet Sci & Technol IUCTC Las Palmas Gran Canaria 35017 Spain Univ La Laguna Dept Comp Engn & Syst San Cristobal De Laguna 38206 Spain Univ Las Palmas Gran Canaria Inst Technol Dev & Innovat Commun IDeTIC Las Palmas Gran Canaria 35017 Spain

We present a computational study whose objective is to show the capacity of the Nitric Oxide (NO) diffusion for information recovery and indexing related to the classical neural architecture sparse distributed memory (SDM). The study is carried out by introducing NO diffusion dynamics by means of a Multi-compartment based NO Diffusion Model in the storage process of the SDM. We develop a new SDM model, which we term sparse distributed memory by Nitric Oxide diffusion (SDM-NO). Both of these architectures were computationally analysed. We have shown that the information indexing guided by the Nitric Oxide dynamics has a similar or slightly better behaviour to the randomly guided indexing by the SDM. Two kinds of patterns were used in the study: a) binary string patterns with eight bits and b) handwritten characters. The indexing guided by the Nitric Oxide dynamics shows a similar or a little bit better behaviour to the guided indexing one performed randomly by the SDM. Nevertheless, we have also shown that both of the architectures do not perform well in these memory processes.

关键词： Mathematical models Indexing Computational modeling Neurotransmitters Behavioral sciences Computer architecture Neurons Artificial neural network nitric oxide nitric oxide dynamic neural-indexing sparse distributed memory

来源：评论

学校读者我要写书评

暂无评论

VSA-based Positional Encoding Can Replace Recurrent Networks in Emergent Symbol Binding 17

VSA-based Positional Encoding Can Replace Recurrent Networks...

引用

17th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy)

作者： Carzaniga, Francesco S. Hersche, Michael Schindler, Kaspar Rahimi, Abbas IBM Res Zurich Ruschlikon Switzerland Bern Univ Bern Univ Hosp Inselspital Dept NeurolSleep Wake Epilepsy Ctr Bern Switzerland Swiss Fed Inst Technol Zurich Switzerland

Variable binding is an open problem in both neuroscience and machine learning relating to how neural circuits combine multiple features into a single entity. Emergent Symbols through Binding in External memory is a recent development tackling variable binding with a compelling solution. An emergent symbolic binding network (ESBN) is able to infer abstract rules through indirection using a dual-stack setup-whereby one stack contains variables and the other contains the associated keys-by autonomously learning a relationship between the two. New keys are generated from previous ones by maintaining a strict time-ordering through the usage of recurrent networks, in particular LSTMs. It is then a natural question whether such an expensive requirement could be replaced by a more economical alternative. In this work, we explore the viability of replacing LSTMs with simpler multi-layer perceptrons (MLPs) by exploiting the properties of high-dimensional spaces through a bundling-based positional encoding. We show how a combination of vector symbolic architectures and appropriate activation functions can achieve and surpass the results reported in the ESBN work, highlighting the role that imbuing the latent space with an explicit structure can play for these unconventional symbolic models.

关键词： Emergent symbolic binding network vector symbolic architectures symbolic reasoning siren sparse distributed memory variable binding recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

A Scalable Cluster-based Hierarchical Hardware Accelerator for a Cortically Inspired Algorithm

引用

ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS 2021年第4期17卷 1–29页

作者： Dey, Sumon Baker, Lee Schabel, Joshua Li, Weifu Franzon, Paul D. North Carolina State Univ Raleigh NC 27695 USA

This article describes a scalable, configurable and cluster-based hierarchical hardware accelerator through custom hardware architecture for sparsey, a cortical learning algorithm. sparsey is inspired by the operation of the human cortex and uses a sparse distributed Representation to enable unsupervised learning and inference in the same algorithm. A distributed on-chip memory organization is designed and implemented in custom hardware to improve memory bandwidth and accelerate the memory read/write operations for synaptic weight matrices. Bit-level data are processed from distributed on-chip memory and custom multiply-accumulate hardware is implemented for binary and fixed-point multiply-accumulation operations. The fixed-point arithmetic and fixed-point storage are also adapted in this implementation. At 16 nm, the custom hardware of sparsey achieved an overall 24.39x speedup, 353.12x energy efficiency per frame, and 1.43x reduction in silicon area against a state-of-the-art GPU.

关键词： Neuromorphic computing accelerator cortical processor hierarchical temporal memory sparse distributed memory

来源：评论

学校读者我要写书评

暂无评论

Analogical mapping and inference with binary spatter codes and sparse distributed memory

Analogical mapping and inference with binary spatter codes a...

引用

International Joint Conference on Neural Networks

作者： Blerim Emruli Ross W. Gayler Fredrik Sandin EISLAB at the Lule? University of Technology 97187 Lule? Sweden Honorary Associate of La Trobe University Bundoora VIC 3086 Australia

ISBN: (纸本)9781467361279

Analogy-making is a key function of human cognition. Therefore, the development of computational models of analogy that automatically learn from examples can lead to significant advances in cognitive systems. Analogies require complex, relational representations of learned structures, which is challenging for both symbolic and neurally inspired models. Vector symbolic architectures (VSAs) are a class of connectionist models for the representation and manipulation of compositional structures, which can be used to model analogy. We study a novel VSA network for the analogical mapping of compositional structures, which integrates an associative memory known as sparse distributed memory (SDM). The SDM enables non-commutative binding of compositional structures, which makes it possible to predict novel patterns in sequences. To demonstrate this property we apply the network to a commonly used intelligence test called Raven's Progressive Matrices. We present results of simulation experiments for the Raven's task and calculate the probability of prediction error at 95% confidence level. We find that non-commutative binding requires sparse activation of the SDM and that 10-20% concept-specific activation of neurons is optimal. The optimal dimensionality of the binary distributed representations of the VSA is of the order 10~4, which is comparable with former results and the average synapse count of neurons in the cerebral cortex.

关键词： sparse distributed memory VSAs SDM

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：