Brain-Score operates on BrainModels. A BrainModel can be treated like an experimental subject, with
methods such as recording from a cortical region and performing a behavioral task (see the
docs).
Many models submitted to Brain-Score are what we call a BaseModel. These are often variants of
models from the machine learning community without a particular commitment to the brain and no
knowledge of what e.g. "V1" is. To engage with these models and for ease-of-use, such BaseModels
are typically converted into BrainModels by making commitments to the brain such as committing
layers to cortical regions on separate datasets.
Layer Commitment
BaseModel layers have to be committed to cortical regions. For BaseModels that are automatically
translated into BrainModels this is done on separate public data.
The same layers are thus used when recording from the same cortical region, e.g. always the same
layer for V1 instead of different layers per benchmark.
No layer commitments found for this model. Older submissions might not have stored this
information but will be updated when evaluated on new benchmarks.
Visual Angle (Degrees): None
Models have to declare their field-of-view so that stimuli can be displayed like they were
displayed to experimental subjects.
For instance, if experimental stimuli were shown at 4 degrees and a model's field-of-view is
larger than that, then the stimuli are padded such that the core stimulus will make up 4 degrees
in the model's field-of-view.
No visual degrees found for this model. The submission might have failed.