Spiking neurons with short-term synaptic plasticity form superior generative networks.
Spiking neurons with short-term synaptic plasticity form superior generative networks.
复制标题
DOI：
10.1038/s41598-018-28999-2
复制
发表时间：
2018-07-13
影响因子：
4.6
通讯作者：
Petrovici MA
中科院分区：
文献类型：
--
作者：
Leng L;Martel R;Breitwieser O;Bytschok I;Senn W;Schemmel J;Meier K;Petrovici MA
执行概率推理的脉冲神经网络，既被作为皮质计算的模型提出，也被作为解决机器学习问题的候选方案。然而，基于脉冲的计算在任何方面优于非脉冲替代方案的证据仍然稀少。我们提出，短期突触可塑性可以为脉冲神经网络提供相较于其经典对应物独特的计算优势。当从高维、多样的数据集中学习时，能量景观中的深度吸引子常常给采样过程带来混合问题。经典算法通过采用各种回火技术来解决这个问题，这些技术在计算上要求很高，并且需要全局状态更新。我们展示了在具有局部短期突触可塑性的脉冲神经网络中如何能实现类似的结果。此外，我们讨论了当训练数据不平衡时，这些网络如何甚至能优于基于回火的方法。因此，我们揭示了一种基于生物学启发的、局部的、由脉冲触发的突触动力学的强大计算特性，它仅仅基于有限的突触资源池，使其能够处理复杂的感官数据。
Spiking networks that perform probabilistic inference have been proposed both as models of cortical computation and as candidates for solving problems in machine learning. However, the evidence for spike-based computation being in any way superior to non-spiking alternatives remains scarce. We propose that short-term synaptic plasticity can provide spiking networks with distinct computational advantages compared to their classical counterparts. When learning from high-dimensional, diverse datasets, deep attractors in the energy landscape often cause mixing problems to the sampling process. Classical algorithms solve this problem by employing various tempering techniques, which are both computationally demanding and require global state updates. We demonstrate how similar results can be achieved in spiking networks endowed with local short-term synaptic plasticity. Additionally, we discuss how these networks can even outperform tempering-based approaches when the training data is imbalanced. We thereby uncover a powerful computational property of the biologically inspired, local, spike-triggered synaptic dynamics based simply on a limited pool of synaptic resources, which enables them to deal with complex sensory data.
登录
查看更多内容
影响因子：
19.9
作者：
Fiser, Jozsef;Berkes, Pietro;Orban, Gergo;Lengyel, Mate
通讯作者：
Lengyel, Mate
影响因子：
25
作者：
Fujisawa, Shigeyoshi;Amarasingham, Asohan;Buzsaki, Gyoergy
通讯作者：
Buzsaki, Gyoergy
影响因子：
64.8
作者：
Jezek, Karel;Henriksen, Espen J.;Moser, May-Britt
通讯作者：
Moser, May-Britt
影响因子：
14.9
作者：
Hinton, Geoffrey;Deng, Li;Kingsbury, Brian
通讯作者：
Kingsbury, Brian
影响因子：
4.3
作者：
Buesing L;Bill J;Nessler B;Maass W
通讯作者：
Maass W