首页/论文/2005.03476

arXiv 2005.034762020-05cs.NEcs.LG

Brain-like approaches to unsupervised learning of hidden representations -- a comparative study

KTH Royal Institute of Technology（瑞典皇家理工学院）；Stockholm University（斯德哥尔摩大学）

Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman

备注：: arXiv admin note: text overlap with arXiv:2003.12415

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Unsupervised learning of hidden representations has been one of the most vibrant research directions in machine learning in recent years. In this work we study the brain-like Bayesian Confidence Propagating Neural Network (BCPNN) model, recently extended to extract sparse distributed high-dimensional representations. The usefulness and class-dependent separability of the hidden representations when trained on MNIST and Fashion-MNIST datasets is studied using an external linear classifier and compared with other unsupervised learning methods that include restricted Boltzmann machines and autoencoders.

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

Using brain inspired principles to unsupervisedly learn good representations for visual pattern recognition

University of Lisbon（里斯本大学）

Although deep learning has solved difficult problems in visual pattern recognition, it is mostly successful in tasks where there are lots of labeled training data available. Furthermore, the global back-propagation based training rule and the amount of employed layers represents a departure from biological inspiration. The brain is able to perform most of these tasks in a very general way from limited to no labeled data. For these reasons it is still a key research question to look into computational principles in the brain that can help guide models to unsupervisedly learn good representation…

2021-04-30cs.CVcs.NE

Brain-inspired self-organization with cellular neuromorphic computing for multimodal unsupervised learning

CNRS（法国国家科学研究中心）；LEAT（电子、天线与电信实验室）

Cortical plasticity is one of the main features that enable our ability to learn and adapt in our environment. Indeed, the cerebral cortex self-organizes itself through structural and synaptic plasticity mechanisms that are very likely at the basis of an extremely interesting characteristic of the human brain development: the multimodal association. In spite of the diversity of the sensory modalities, like sight, sound and touch, the brain arrives at the same concepts (convergence). Moreover, biological observations show that one modality can activate the internal representation of another mod…

2020-09-02cs.LGcs.NEq-bio.NC

Making a Spiking Net Work: Robust brain-like unsupervised machine learning

University of Technology Sydney（悉尼科技大学）；Cuvos Pty. Ltd.（Cuvos私人有限公司）；Queensland University of Technology（昆士兰科技大学）

The surge in interest in Artificial Intelligence (AI) over the past decade has been driven almost exclusively by advances in Artificial Neural Networks (ANNs). While ANNs set state-of-the-art performance for many previously intractable problems, the use of global gradient descent necessitates large datasets and computational resources for training, potentially limiting their scalability for real-world domains. Spiking Neural Networks (SNNs) are an alternative to ANNs that use more brain-like artificial neurons and can use local unsupervised learning to rapidly discover sparse recognizable feat…

2022-09-01cs.AIcs.CVcs.LG

在类脑前馈神经网络中利用赫布突触与结构可塑性进行无监督表征学习

Unsupervised representation learning with Hebbian synaptic and structural plasticity in brain-like feedforward neural networks

本文提出融合皮层柱、赫布突触与结构可塑性等机制的前馈BCPNN模型，用于无监督表征学习，并在图像、QSAR和恶意软件检测基准上取得与MLP及先进类脑网络相当的性能。

2025-01-09cs.NEq-bio.NC

用于在线无监督时间序列预测的脑启发脉冲神经网络

Brain-Inspired Spiking Neural Network for Online Unsupervised Time Series Prediction

Georgia Institute of Technology（佐治亚理工学院）

本文提出CLURSNN模型，结合STDP、随机延迟嵌入和基于Wasserstein距离的拓扑数据分析，实现能量与数据高效的在线无监督时间序列预测，并在Lorenz63系统上优于现有DNN方法。

2023-05-31cs.AIcs.LGcs.NE

类睡眠的无监督重放在数据有限或不平衡时提升性能

Sleep-Like Unsupervised Replay Improves Performance when Data are Limited or Unbalanced

Del Norte High School（德尔诺特高中）；University of California, San Diego（加州大学圣地亚哥分校）

本研究提出在ANNs中引入基于局部Hebbian学习规则的类睡眠无监督重放阶段，显著提升了在数据有限或不平衡条件下的模型准确率，揭示了大脑睡眠期间增强记忆的突触权重动态策略。

2024-02-12cs.LGcs.NE

更多相关论文收起更多论文

On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs

Neuromorphic computing is emerging to be a disruptive computational paradigm that attempts to emulate various facets of the underlying structure and functionalities of the brain in the algorithm and hardware design of next-generation machine learning platforms. This work goes beyond the focus of current neuromorphic computing architectures on computational models for neuron and synapse to examine other computational units of the biological brain that might contribute to cognition and especially self-repair. We draw inspiration and insights from computational neuroscience regarding functionalit…

2020-11-16cs.NE

Bio-plausible Unsupervised Delay Learning for Extracting Temporal Features in Spiking Neural Networks

The plasticity of the conduction delay between neurons plays a fundamental role in learning. However, the exact underlying mechanisms in the brain for this modulation is still an open problem. Understanding the precise adjustment of synaptic delays could help us in developing effective brain-inspired computational models in providing aligned insights with the experimental evidence. In this paper, we propose an unsupervised biologically plausible learning rule for adjusting the synaptic delays in spiking neural networks. Then, we provided some mathematical proofs to show that our learning rule …

2020-11-18cs.NEq-bio.NC

一种受生物可信学习规则与连接启发的、基于STDP的无监督脉冲神经网络

An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections

本文提出融合自适应突触滤波、脉冲阈值、侧向抑制及STB-STDP的无监督SNN，在MNIST、FashionMNIST和CIFAR10上取得领先表现。

2023-04-22cs.NE

BHN: A Brain-like Heterogeneous Network

The human brain works in an unsupervised way, and more than one brain region is essential for lighting up intelligence. Inspired by this, we propose a brain-like heterogeneous network (BHN), which can cooperatively learn a lot of distributed representations and one global attention representation. By optimizing distributed, self-supervised, and gradient-isolated objective functions in a minimax fashion, our model improves its representations, which are generated from patches of pictures or frames of videos in experiments.

2020-06-06cs.AIcs.NE

A comparative analysis of methods for estimating axon diameter using DWI

The importance of studying the brain microstructure is described and the existing and state of the art non-invasive methods for the investigation of the brain microstructure using Diffusion Weighted Magnetic Resonance Imaging (DWI) is studied. In the next step, Cramer-Rao Lower Bound (CRLB) analysis is described and utilised for assessment of the minimum estimation error and uncertainty level of different Diffusion Weighted Magnetic Resonance (DWMR) signal decay models. The analyses are performed considering the best scenario through which, we assume that the models are the appropriate represe…

2013-11-12cs.NE

利用脑启发脉冲神经网络的高级计算及相关应用

Advanced Computing and Related Applications Leveraging Brain-inspired Spiking Neural Networks

本文综述了脉冲神经网络在脑启发人工智能中的核心计算与应用，系统分析了五种神经元模型、五种网络拓扑结构及多类学习算法，并重点回顾了国内外类脑神经形态芯片的研究进展，为该领域新手提供学习概念与研究方向。

2023-09-08cs.AIcs.NE

Nonlinear Dynamics of Binocular Rivalry: A Comparative Study

When our eyes are presented with the same image, the brain processes it to view it as a single coherent one. The lateral shift in the position of our eyes, causes the two images to possess certain differences, which our brain exploits for the purpose of depth perception and to gauge the size of objects at different distances, a process commonly known as stereopsis. However, when presented with two different visual stimuli, the visual awareness alternates. This phenomenon of binocular rivalry is a result of competition between the corresponding neuronal populations of the two eyes. The article …

2018-11-25cs.NEq-bio.NC

不变性变换的无监督学习

Unsupervised Learning of Invariance Transformations

本文提出通过无监督 Hebbian 学习在循环突触连接中形成近似图对称性，并开发寻找加权图近似自同构的算法框架，从而从小样本结构中恢复不变性变换。

2023-07-24cs.NE

Control of synaptic plasticity via the fusion of reinforcement learning and unsupervised learning in neural networks

The brain can learn to execute a wide variety of tasks quickly and efficiently. Nevertheless, most of the mechanisms that enable us to learn are unclear or incredibly complicated. Recently, considerable efforts have been made in neuroscience and artificial intelligence to understand and model the structure and mechanisms behind the amazing learning capability of the brain. However, in the current understanding of cognitive neuroscience, it is widely accepted that synaptic plasticity plays an essential role in our amazing learning capability. This mechanism is also known as the Credit Assignmen…

2023-03-26cs.AIcs.LGcs.NE