当前位置:
X-MOL 学术
›
arXiv.cs.NE
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Short-term synaptic plasticity optimally models continuous environments
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2020-09-15 , DOI: arxiv-2009.06808 Timoleon Moraitis, Abu Sebastian, Evangelos Eleftheriou (IBM Research - Zurich)
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2020-09-15 , DOI: arxiv-2009.06808 Timoleon Moraitis, Abu Sebastian, Evangelos Eleftheriou (IBM Research - Zurich)
Biological neural networks operate with extraordinary energy efficiency,
owing to properties such as spike-based communication and synaptic plasticity
driven by local activity. When emulated in silico, such properties also enable
highly energy-efficient machine learning and inference systems. However, it is
unclear whether these mechanisms only trade off performance for efficiency or
rather they are partly responsible for the superiority of biological
intelligence. Here, we first address this theoretically, proving rigorously
that indeed the optimal prediction and inference of randomly but continuously
transforming environments, a common natural setting, relies on adaptivity
through short-term spike-timing dependent plasticity, a hallmark of biological
neural networks. Secondly, we assess this theoretical optimality via
simulations and also demonstrate improved artificial intelligence (AI). For the
first time, a largely biologically modelled spiking neural network (SNN)
surpasses state-of-the-art artificial neural networks (ANNs) in all relevant
aspects, in an example task of recognizing video frames transformed by moving
occlusions. The SNN recognizes the frames more accurately, even if trained on
few, still, and untransformed images, with unsupervised and synaptically-local
learning, binary spikes, and a single layer of neurons - all in contrast to the
deep-learning-trained ANNs. These results indicate that on-line adaptivity and
spike-based computation may optimize natural intelligence for natural
environments. Moreover, this expands the goal of exploiting biological
neuro-synaptic properties for AI, from mere efficiency, to computational
supremacy altogether.
中文翻译:
短期突触可塑性以最佳方式模拟连续环境
由于基于尖峰的通信和由局部活动驱动的突触可塑性等特性,生物神经网络以非凡的能源效率运行。在计算机模拟时,这些特性还可以实现高能效的机器学习和推理系统。然而,尚不清楚这些机制是否只是为了效率而牺牲性能,或者更确切地说,它们是生物智能优势的部分原因。在这里,我们首先从理论上解决这个问题,严格证明随机但不断变化的环境(一种常见的自然环境)的最佳预测和推理确实依赖于通过短期尖峰时间依赖性可塑性(生物神经网络的标志)的适应性。第二,我们通过模拟评估了这种理论最优性,并展示了改进的人工智能 (AI)。在识别由移动遮挡转换的视频帧的示例任务中,主要生物建模的尖峰神经网络 (SNN) 在所有相关方面都首次超越了最先进的人工神经网络 (ANN)。SNN 可以更准确地识别帧,即使是在少量、静止和未转换的图像上进行训练,具有无监督和突触局部学习、二进制尖峰和单层神经元 - 所有这些都与深度学习训练的 ANN 形成对比。这些结果表明,在线自适应和基于尖峰的计算可以优化自然环境的自然智能。此外,这扩展了为人工智能开发生物神经突触特性的目标,
更新日期:2020-09-16
中文翻译:
短期突触可塑性以最佳方式模拟连续环境
由于基于尖峰的通信和由局部活动驱动的突触可塑性等特性,生物神经网络以非凡的能源效率运行。在计算机模拟时,这些特性还可以实现高能效的机器学习和推理系统。然而,尚不清楚这些机制是否只是为了效率而牺牲性能,或者更确切地说,它们是生物智能优势的部分原因。在这里,我们首先从理论上解决这个问题,严格证明随机但不断变化的环境(一种常见的自然环境)的最佳预测和推理确实依赖于通过短期尖峰时间依赖性可塑性(生物神经网络的标志)的适应性。第二,我们通过模拟评估了这种理论最优性,并展示了改进的人工智能 (AI)。在识别由移动遮挡转换的视频帧的示例任务中,主要生物建模的尖峰神经网络 (SNN) 在所有相关方面都首次超越了最先进的人工神经网络 (ANN)。SNN 可以更准确地识别帧,即使是在少量、静止和未转换的图像上进行训练,具有无监督和突触局部学习、二进制尖峰和单层神经元 - 所有这些都与深度学习训练的 ANN 形成对比。这些结果表明,在线自适应和基于尖峰的计算可以优化自然环境的自然智能。此外,这扩展了为人工智能开发生物神经突触特性的目标,