Department of Computer Science, Middlesex University, London, UK.
Cogn Neurodyn. 2014 Aug;8(4):299-311. doi: 10.1007/s11571-014-9282-4. Epub 2014 Jan 30.
A system with some degree of biological plausibility is developed to categorise items from a widely used machine learning benchmark. The system uses fatiguing leaky integrate and fire neurons, a relatively coarse point model that roughly duplicates biological spiking properties; this allows spontaneous firing based on hypo-fatigue so that neurons not directly stimulated by the environment may be included in the circuit. A novel compensatory Hebbian learning algorithm is used that considers the total synaptic weight coming into a neuron. The network is unsupervised and entirely self-organising. This is relatively effective as a machine learning algorithm, categorising with just neurons, and the performance is comparable with a Kohonen map. However the learning algorithm is not stable, and behaviour decays as length of training increases. Variables including learning rate, inhibition and topology are explored leading to stable systems driven by the environment. The model is thus a reasonable next step toward a full neural memory model.
开发了一个具有一定生物学合理性的系统，用于对广泛使用的机器学习基准中的项目进行分类。该系统使用疲劳漏积分和放电神经元，这是一种相对粗糙的点模型，大致复制了生物尖峰特性；这允许基于 Hypo-fatigue 的自发发射，以便未直接受环境刺激的神经元可以被包含在电路中。使用了一种新颖的补偿赫布学习算法，该算法考虑了进入神经元的总突触权重。网络是无监督的，完全是自我组织的。作为一种机器学习算法，它的效果相对较好，仅使用神经元进行分类，性能可与 Kohonen 图相媲美。然而，学习算法不稳定，随着训练长度的增加，性能会下降。探索了包括学习率、抑制和拓扑在内的变量，从而得到了由环境驱动的稳定系统。因此，该模型是实现全神经记忆模型的合理下一步。
