Fig 1.
Framework for constructing MouseNet from biological constraints on anatomy, via publicly available data from large-scale experiments. The CNN architecture is set by the analysis of hierarchy [25] on the Allen Mouse Brain Connectivity Atlas (http://connectivity.brain-map.org) [22]; and the meta-parameters are mostly fixed by the combination of the 100-micrometer resolution interareal connectome [23] with detailed estimates of neuron density [38], and the statistics of connections between cortical layers from the literature [39–41].
Fig 2.
Illustration of MouseNet architecture.
Only feedforward connections are included. (A) High-level organization of MouseNet, based on analysis of the hierarchy of lateral visual areas ([25]). (B) Connection patterns at the level of cortical layers. (C) Full MouseNet architecture.
Fig 3.
From mouse brain to CNN model.
(A) From mouse brain hierarchy to CNN architecture. (B) An example of Conv operation with Gaussian mask. (C) ReLU operation in the CNN architecture. (D) The binary Gaussian mask is generated by a Gaussian shaped probability whose peak and width are meta-parameters.
Table 1.
Exitatory population density [mm−3] [38].
Table 2.
Number of 10μm voxels in each region.
Table 3.
Estimated number of exitatory neurons in each region.
Table 4.
Estimated Gaussian width for interlaminar excitatory connections.
The values outside of the parenthesis are extracted from [41]; the values inside the parenthesis are scaled to mouse cortex, using the width 114 μm for L4-to-L4 connections in mouse auditory cortex [40]. Units are micrometers (μm).
Table 5.
The connection probability between excitatory populations offset at 75 micrometer .
The numbers are from Fig 4A in [39]). The calculated Gaussian peak probability are given in parenthesis.
Table 6.
Area size (mm2) estimated from the voxel model.
Table 7.
The calculated meta-parameters for the Conv layers.
Table 8.
Parameters from data or assumptions.
Table 9.
Meta-parameters for Conv layer connecting source area i to target area j.
Table 10.
Number of parameters for MouseNet and VGG16 for 1000-class ImageNet classification task.
Table 11.
Number of neurons recorded from each mouse brain region.
Fig 4.
Selecting reliable neurons improves noise ceilings.
(Left) Reliability distribution of neural populations. Each row shows all the brain areas at a specific cortical layer. The dotted lines indicate the median reliability of each neural population. (Right) The noise ceilings change with variation of the threshold for selecting reliable neurons. The higher the threshold, the fewer neurons are selected. For some populations, selecting a certain portion of reliable neurons gives best noise ceiling. Error bars are from different draws of non-overlapping trials.
Fig 5.
Summary plot of median reliability and best noise ceiling for each brain area.
Each color represents a different brain area, and shades from light to dark indicate different cortical layers L2/3, L4 and L5. The circle size is proportional to the size of the population in the dataset.
Fig 6.
SSM between mouse data in VISp(top)/VISl(middle)/VISal(bottom) L2/3 and all layers in the MouseNet before (blue) and after training (red).
Each line corresponds to the mean of four different MouseNet instances trained from different initialization weights (dots). The x axis includes all the layers in the model in a serial way. The five parallel secondary visual area pathways in the model are in shaded grey background. Black stars denote the the pvalues of two-sample t-test with Benjamini/Hochberg correction of 22 comparisons within one brain area is less than 0.05; Red stars denote the pvalues of two-sample t-test with Benjamini/Hochberg correction of all 9x22 comparisons across all 9 brain areas is less than 0.05.
Fig 7.
SSM between best layer in trained VGG16/MouseNet and mouse brain regions.
The plot shows results of 3 instances of VGG16 (with validation accuracy 60.46, 60.72, 60.93) and 4 instances of MouseNet (with validation accuracy 37.46, 37.95, 37.52, 37.49) trained from different initialization weights. Yellow lines denote the best noise ceiling; their widths are standard deviations calculated from multiple draws of non-overlapping trials as in Fig 4. Dotted black lines are the SSM values between the 64x64 pixel input and the corresponding regions. Black stars denote the statistical significance of two-sample t-test between the mean of the trained VGG16 and the trained MouseNet instances (one star: p < 0.05, two stars: p < 0.01, three stars: p < 0.001).
Fig 8.
Functional similarity and validation accuracy during the training process.
Each row compares models with a different brain area. We show one instance of MouseNet and VGG16 during their training process, where each dot represents the best layer’s SSM of one model at a certain epoch to the specified brain area. The clear jumps of validation accuracy occurred when the learning rate is reduced.
Fig 9.
Distributions of lifetime sparseness (top row) and circular selectivity index (bottom row) for all the units in the models and all the neurons in the mouse data.
The distributions of all units in one instance of trained/untrained MouseNet (first column) and VGG16 (second column) are plotted along with mouse data, with the Jensen-Shannon distances between the models and the data annotated. The Jensen-Shannon distances between multiple instances of models and the mouse data are summarized in the third column. Black stars denote the statistical significance of two-sample t-test between the mean of the model instances (one star: p < 0.05, two stars: p < 0.01, three stars: p < 0.001).
Fig 10.
Visualization of all layers from one instance (left) and three instances (right) of trained/untrained MouseNet and VGG16.
Each dot represents a layer from a certain model instance. The position of the dots are the two-dimensional projection from the multidimensional scaling algorithm, with the distance measure defined as one minus the SSM value.
Table 12.
Diversity index of model layers.