Adelsberger-Mangan D M, Levy W B
Department of Biomedical Engineering, University of Virginia Health Sciences Center, Charlottesville 22908.
Biol Cybern. 1993;70(1):81-7. doi: 10.1007/BF00202569.
This report demonstrates the effectiveness of two processes in constructing simple feedforward networks which perform good transformations on their inputs. Good transformations are characterized by the minimization of two information measures: the information loss incurred with the transformation and the statistical dependency of the output. The two processes build appropriate synaptic connections in initially unconnected networks. The first process, synaptogenesis, creates new synaptic connections; the second process, associative synaptic modification, adjusts the connection strength of existing synapses. Synaptogenesis produces additional innervation for each output neuron until each output neuron achieves a firing rate of approximately 0.50. Associative modification of existing synaptic connections lends robustness to network construction by adjusting suboptimal choices of initial synaptic weights. Networks constructed using synaptogenesis and synaptic modification successfully preserve the information content of a variety of inputs. By recording a high-dimensional input into an output of much smaller dimension, these networks drastically reduce the statistical dependence of neuronal representations. Networks constructed with synaptogenesis and associative modification perform good transformations over a wide range of neuron firing thresholds.
本报告展示了两种构建简单前馈网络的过程的有效性，这些网络能对其输入进行良好的变换。良好的变换以两种信息度量的最小化为特征：变换过程中产生的信息损失以及输出的统计依赖性。这两种过程在最初未连接的网络中建立适当的突触连接。第一个过程，突触发生，创建新的突触连接；第二个过程，关联突触修饰，调整现有突触的连接强度。突触发生为每个输出神经元产生额外的神经支配，直到每个输出神经元达到约0.50的放电率。对现有突触连接的关联修饰通过调整初始突触权重的次优选择，增强了网络构建的稳健性。使用突触发生和突触修饰构建的网络成功地保留了各种输入的信息内容。通过将高维输入记录到维度小得多的输出中，这些网络极大地降低了神经元表征的统计依赖性。用突触发生和关联修饰构建的网络在很宽的神经元放电阈值范围内都能进行良好的变换。
