Spiking Neural Networks for Computer Vision

EVS ------------------------------ Root directory: EVS Description of data: 1. Multiscale representation: > INPUT FILES: The first digit of the MNIST dataset was converted using an EVS (pyDVS) emulator and stored as (neuron id, time stamps) pairs. These were stored as text and compressed using the bzip2 Python package, resulting in the file mnist_img_00000_class_5.txt.bz2 . 2. Motion sensing: > INPUT FILES: Images representing a boucing ball are stored in the bouncing_ball_sequence_w_064_h_064_bw_05.zip archive file, these were processed with an EVS emulator and results in the input file for the experiment bouncing_ball_sequence_w_064_h_064_bw_05___spikes.txt.bz2 . The files correct_0_0_3.txt and incorrect_0_0_3.txt are to be processed to generate voltage curves shown in the paper, they contain membrane voltage and slow neurotransmitter levels through the steps of a simulation. > OUTPUT FILES: Motion sensing results can be found in motion_outputs___2018-02-27-12-47.pickle.bz2 , this contains a dictionary of spike arrays for each population measured during the experiments. They were stored using the standard Python pickle format and later compressed using the bzip2 Python package. ====================== MNIST Structural plasticity ------------------------------ Root directory: MNIST Structural plasticity > INPUT FILES: the input MNIST Digits which are loaded into the mnist_topographic_map.py or mnist_topographic_map_rate_based.py scripts (as exemplified in open_rate_files.ipynb) > RESULT FILES: contains the connectivity, spiking activity and parameters used for training and for testing The results are contained within numpy .npz files and are contained within the RESULT FILES folder. If the files' names start with "testing" then the file contains results from the testing phase of the network, conversely, the ones with prefix (starting with mnist_case_*...) contain post-training network information. Case 1 refers to networks in which both synaptic plasticity and structural plasticity operate at the same time, while in case 3 synapses have static weight, but the connectivity changes in real time. Case 2 is case 3 without lateral connectivity. The structure of the .npz data files can be interrogated in python. To this end, the iPython (Jupyter) notebooks (.ipynb) show how this connectivity/activity can be extracted and analysed. The data which contains the description "rate_based" in the name is to be analysed with the notebook "Large-scale MNIST network - rate based.ipynb", while the ones with description "cs_on_off " is to be analysed with the notebook "Large-scale MNIST network 2 source inputs.ipynb". ====================== Maximum entropy sampling ------------------------------ Root directory: Maximum entropy > input: pre-processed image and label data from the MNIST training set required by the C code ======================

EVS ------------------------------ 根目录：EVS
数据描述：
1. 多尺度表征：
> 输入文件：将MNIST数据集的首张数字图像通过EVS（pyDVS）模拟器转换，存储为（神经元ID，时间戳）对。这些数据以文本格式保存，并通过Python的bzip2工具包进行压缩，最终生成文件mnist_img_00000_class_5.txt.bz2。
2. 运动感知：
> 输入文件：代表弹跳小球的图像存储于bouncing_ball_sequence_w_064_h_064_bw_05.zip归档文件中，经EVS模拟器处理后，得到本实验的输入文件bouncing_ball_sequence_w_064_h_064_bw_05___spikes.txt.bz2。文件correct_0_0_3.txt与incorrect_0_0_3.txt用于生成论文中展示的电压曲线，二者包含模拟过程各阶段的膜电压与慢速神经递质水平数据。
> 输出文件：运动感知结果存储于motion_outputs___2018-02-27-12-47.pickle.bz2，该文件包含实验中测得的各神经元集群的脉冲阵列字典，采用标准Python pickle格式存储，后经Python的bzip2工具压缩。
====================== MNIST Structural plasticity ------------------------------ 根目录：MNIST 结构可塑性
> 输入文件：输入的MNIST手写数字数据集将被加载至mnist_topographic_map.py或mnist_topographic_map_rate_based.py脚本中（具体使用示例可参考open_rate_files.ipynb）
> 结果文件：包含训练与测试阶段使用的连接权重、脉冲活动与参数，结果存储于numpy的.npz格式文件中，存放于RESULT FILES文件夹内。若文件名以"testing"开头，则该文件包含网络测试阶段的结果；反之，以"mnist_case_*..."为前缀的文件包含训练完成后的网络信息。
案例1指同时运行突触可塑性与结构可塑性的网络；案例3中突触权重固定，但连接关系可实时更新；案例2为移除侧向连接后的案例3。可在Python中查询.npz数据文件的结构，相关操作可参考iPython（Jupyter）笔记本文件（.ipynb），其中展示了如何提取并分析该连接与活动数据。
文件名中包含"rate_based"的数据集需通过笔记本文件"Large-scale MNIST network - rate based.ipynb"进行分析，而包含"cs_on_off"的数据集则需通过"Large-scale MNIST network 2 source inputs.ipynb"进行分析。
====================== Maximum entropy sampling ------------------------------ 根目录：Maximum entropy
> 输入：C代码所需的经过预处理的MNIST训练集图像与标签数据。