arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1604.05459cs.NE
收藏

一种在线构造塑性规则用于生成更好的储层

An Online Structural Plasticity Rule for Generating Better Reservoirs

Subhrajit Roy, Arindam Basu

摘要:

本文提出了一种新的神经启发式低分辨率在线无监督学习规则,用于训练液态机的储液器。这种液体是一个稀疏互连的巨大的周期性神经元网络。所提出的学习规则的灵感来自于结构可塑性,并通过突触连接的形成和消除来训练液体。因此,这种学习涉及到重新连接储库连接,类似于在生物神经网络中观察到的结构可塑性。网络连接可以存储为连接矩阵,并通过使用通常在神经形态系统中采用的地址事件表示(AER)协议在存储器中更新。在研究“成对分离特性”时,我们发现,与随机液体相比,训练液体提供1.36 $\pm$ 0.18倍的类间分离,同时保持类似的类内分离。此外,对“线性分离特性”的分析表明,训练液体比随机液体好2.05 $\pm$ 0.27倍。此外,我们表明,我们的液体是能够保留的“泛化”能力和“一般性”的随机液体。记忆分析表明,训练过的液体具有比随机液体长83.67 $\pm$ 5.79 ms的衰落记忆,随机液体对于特定类型的尖峰训练输入显示出92.8 $\pm$ 5.03 ms的衰落记忆。我们还抛出一些光的动态的液体内的经常性连接的演变。此外,与最近提出的用于迭代细化储层的“分离驱动突触修改”算法相比,我们的学习规则分别为四类、八类和十二类模式识别任务提供了9.30%、15.21%和12.52%的液体分离和2.8%、9.1%和7.9%的分类准确率。

英文摘要:

In this article, a novel neuro-inspired low-resolution online unsupervised learning rule is proposed to train the reservoir or liquid of Liquid State Machine. The liquid is a sparsely interconnected huge recurrent network of spiking neurons. The proposed learning rule is inspired from structural plasticity and trains the liquid through formation and elimination of synaptic connections. Hence, the learning involves rewiring of the reservoir connections similar to structural plasticity observed in biological neural networks. The network connections can be stored as a connection matrix and updated in memory by using Address Event Representation (AER) protocols which are generally employed in neuromorphic systems. On investigating the 'pairwise separation property' we find that trained liquids provide 1.36 $\pm$ 0.18 times more inter-class separation while retaining similar intra-class separation as compared to random liquids. Moreover, analysis of the 'linear separation property' reveals that trained liquids are 2.05 $\pm$ 0.27 times better than random liquids. Furthermore, we show that our liquids are able to retain the 'generalization' ability and 'generality' of random liquids. A memory analysis shows that trained liquids have 83.67 $\pm$ 5.79 ms longer fading memory than random liquids which have shown 92.8 $\pm$ 5.03 ms fading memory for a particular type of spike train inputs. We also throw some light on the dynamics of the evolution of recurrent connections within the liquid. Moreover, compared to 'Separation Driven Synaptic Modification' - a recently proposed algorithm for iteratively refining reservoirs, our learning rule provides 9.30%, 15.21% and 12.52% more liquid separations and 2.8%, 9.1% and 7.9% better classification accuracies for four, eight and twelve class pattern recognition tasks respectively.

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。

↑