首页/论文/2006.04716

arXiv 2006.047162020-06-08cs.NEcs.LG

Energy Constraints Improve Liquid State Machine Performance

Rochester Institute of Technology（罗切斯特理工学院）

Andrew Fountain, Cory Merkel

备注：: 8 pages, 5 figures. Submitted to ICONS 2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

A model of metabolic energy constraints is applied to a liquid state machine in order to analyze its effects on network performance. It was found that, in certain combinations of energy constraints, a significant increase in testing accuracy emerged; an improvement of 4.25% was observed on a seizure detection task using a digital liquid state machine while reducing overall reservoir spiking activity by 6.9%. The accuracy improvements appear to be linked to the energy constraints' impact on the reservoir's dynamics, as measured through metrics such as the Lyapunov exponent and the separation of the reservoir.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Liquid State Machines in Adbiatic Quantum Computers for General Computation

Major mistakes do not read

2011-07-08cs.CCcs.NE

Research on the Concept of Liquid State Machine

Liquid State Machine (LSM) is a neural model with real time computations which transforms the time varying inputs stream to a higher dimensional space. The concept of LSM is a novel field of research in biological inspired computation with most research effort on training the model as well as finding the optimum learning method. In this review, the performance of LSM model was investigated using two learning method, online learning and offline (batch) learning methods. The review revealed that optimal performance of LSM was recorded through online method as computational space and other comple…

2019-10-08cs.NE

Liquid State Machines的动态训练

Dynamic Training of Liquid State Machines

本研究通过确定SNN中最有效的权重分配范围以最小化期望与实际输出的差异，优化了Liquid State Machines的训练过程，并验证了Barabasi-Albert随机图方法在权重初始化中表现最佳。

2023-09-10cs.NE

Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity

Rutgers University（罗格斯大学）

The liquid state machine (LSM) combines low training complexity and biological plausibility, which has made it an attractive machine learning framework for edge and neuromorphic computing paradigms. Originally proposed as a model of brain computation, the LSM tunes its internal weights without backpropagation of gradients, which results in lower performance compared to multi-layer neural networks. Recent findings in neuroscience suggest that astrocytes, a long-neglected non-neuronal brain cell, modulate synaptic plasticity and brain dynamics, tuning brain networks to the vicinity of the comput…

2021-10-26cs.CVcs.LGcs.NE

A Digital Neuromorphic Architecture Efficiently Facilitating Complex Synaptic Response Functions Applied to Liquid State Machines

Information in neural networks is represented as weighted connections, or synapses, between neurons. This poses a problem as the primary computational bottleneck for neural networks is the vector-matrix multiply when inputs are multiplied by the neural network weights. Conventional processing architectures are not well suited for simulating neural networks, often requiring large amounts of energy and time. Additionally, synapses in biological neural networks are not binary connections, but exhibit a nonlinear response function as neurotransmitters are emitted and diffuse between neurons. Inspi…

2017-03-21cs.NEq-bio.NCstat.ML

A Neural Architecture Search based Framework for Liquid State Machine Design

Liquid State Machine (LSM), also known as the recurrent version of Spiking Neural Networks (SNN), has attracted great research interests thanks to its high computational power, biological plausibility from the brain, simple structure and low training complexity. By exploring the design space in network architectures and parameters, recent works have demonstrated great potential for improving the accuracy of LSM model with low complexity. However, these works are based on manually-defined network architectures or predefined parameters. Considering the diversity and uniqueness of brain structure…

2020-04-07cs.NE

更多相关论文收起更多论文

Reservoirs learn to learn

We consider reservoirs in the form of liquid state machines, i.e., recurrently connected networks of spiking neurons with randomly chosen weights. So far only the weights of a linear readout were adapted for a specific task. We wondered whether the performance of liquid state machines can be improved if the recurrent weights are chosen with a purpose, rather than randomly. After all, weights of recurrent connections in the brain are also not assumed to be randomly chosen. Rather, these weights were probably optimized during evolution, development, and prior learning experiences for specific ta…

2019-09-30cs.NE

PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection

Indian Statistical Institute（印度统计研究所）；IIT Kharagpur（印度理工学院克勒格布尔分校）；Østfold University College（东福尔大学学院）

Reservoir Computing (RC) offers a viable option to deploy AI algorithms on low-end embedded system platforms. Liquid State Machine (LSM) is a bio-inspired RC model that mimics the cortical microcircuits and uses spiking neural networks (SNN) that can be directly realized on neuromorphic hardware. In this paper, we present a novel Parallelized LSM (PLSM) architecture that incorporates spatio-temporal read-out layer and semantic constraints on model output. To the best of our knowledge, such a formulation has been done for the first time in literature, and it offers a computationally lighter alt…

2021-05-06cs.AIcs.CVcs.NE

Predicting Performance using Approximate State Space Model for Liquid State Machines

Liquid State Machine (LSM) is a brain-inspired architecture used for solving problems like speech recognition and time series prediction. LSM comprises of a randomly connected recurrent network of spiking neurons. This network propagates the non-linear neuronal and synaptic dynamics. Maass et al. have argued that the non-linear dynamics of LSMs is essential for its performance as a universal computer. Lyapunov exponent (mu), used to characterize the "non-linearity" of the network, correlates well with LSM performance. We propose a complementary approach of approximating the LSM dynamics with a…

2019-01-18cs.NE

Liquid State Machine with Dendritically Enhanced Readout for Low-power, Neuromorphic VLSI Implementations

In this paper, we describe a new neuro-inspired, hardware-friendly readout stage for the liquid state machine (LSM), a popular model for reservoir computing. Compared to the parallel perceptron architecture trained by the p-delta algorithm, which is the state of the art in terms of performance of readout stages, our readout architecture and learning algorithm can attain better performance with significantly less synaptic resources making it attractive for VLSI implementation. Inspired by the nonlinear properties of dendrites in biological neurons, our readout stage incorporates neurons having …

2014-11-20cs.ETcs.NE

利用液态状态机推进射电天文中的射频干扰检测

Advancing RFI-Detection in Radio Astronomy with Liquid State Machines

International Centre for Radio Astronomy Research（国际射电天文研究中心）；University of Western Australia（西澳大学）

本文利用液态状态机改进射电天文中的射频干扰检测，采用二阶泄漏积分和放电神经元和Transformer解码器，实现98%像素精度和0.743 F1分数。

2025-04-14astro-ph.IMcs.NE

Hardware-Friendly Synaptic Orders and Timescales in Liquid State Machines for Speech Classification

Indian Institute of Technology, Bombay（孟买印度理工学院）；Aalto University（阿尔托大学）

Liquid State Machines are brain inspired spiking neural networks (SNNs) with random reservoir connectivity and bio-mimetic neuronal and synaptic models. Reservoir computing networks are proposed as an alternative to deep neural networks to solve temporal classification problems. Previous studies suggest 2nd order (double exponential) synaptic waveform to be crucial for achieving high accuracy for TI-46 spoken digits recognition. The proposal of long-time range (ms) bio-mimetic synaptic waveforms is a challenge to compact and power efficient neuromorphic hardware. In this work, we analyze the r…

2021-04-29cs.NEcs.SDeess.AS