受显著性影响的神经网络
Salience-Affected Neural Networks
摘要：
我们提出了一个简单的神经网络模型，它结合了一个本地连接的前馈结构，传统上用于模拟神经元间的连接，与一层未分化的连接模型的扩散预测从人类边缘系统的皮层。这一新层使得在本地网络处理特定任务或本地信息的同时，可以对全局效应（如显著性）进行建模。这个简单的组合网络显示了显着性和常规处理之间的相互作用，这与发育中的大脑中的已知效应相对应，例如由于情感增强而增强的学习。皮质通过使用从边缘系统到皮质的弥散投射来偏置神经元反应以影响学习和记忆。标准的人工神经网络不模拟这种由上升系统代表的非局部信息流，这是大脑结构的一个重要特征，尽管它们确实允许通过多次试验进行关联学习，但它们根本不提供一次性学习的能力。在这项研究中，我们使用人工神经网络（ANN），创建一个显着性影响的神经网络（SANN）的影响。我们适应人工神经网络体现的能力，以响应输入的显着性信号，并在测试过程中产生一个反向显着性信号。研究表明，与训练数据集合中的输入相似的输入组合在测试期间将产生相似的反向显著性信号。此外，这项研究还发现了一种新的方法，用于通过单次训练迭代来训练ANN。
英文摘要：
We present a simple neural network model which combines a locally-connected feedforward structure, as is traditionally used to model inter-neuron connectivity, with a layer of undifferentiated connections which model the diffuse projections from the human limbic system to the cortex. This new layer makes it possible to model global effects such as salience, at the same time as the local network processes task-specific or local information. This simple combination network displays interactions between salience and regular processing which correspond to known effects in the developing brain, such as enhanced learning as a result of heightened affect. The cortex biases neuronal responses to affect both learning and memory, through the use of diffuse projections from the limbic system to the cortex. Standard ANNs do not model this non-local flow of information represented by the ascending systems, which are a significant feature of the structure of the brain, and although they do allow associational learning with multiple-trial, they simply don't provide the capacity for one-time learning. In this research we model this effect using an artificial neural network (ANN), creating a salience-affected neural network (SANN). We adapt an ANN to embody the capacity to respond to an input salience signal and to produce a reverse salience signal during testing. This research demonstrates that input combinations similar to the inputs in the training data sets will produce similar reverse salience signals during testing. Furthermore, this research has uncovered a novel method for training ANNs with a single training iteration.
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。
