The models were then trained to identify either the auditory or visual stimuli based on an attention cue. The visual bias not only persisted, but helped the brainlike model learn to ignore distracting audio more quickly than other models.

We found that the brain-based model still had a visual bias even after being trained on auditory tasks. But, this bias didn’t hamper the model’s overall performance, and it mimics a consistently observed human visual bias (Posner et al 1974)

Conversely, when trained on a similar set of auditory categorization tasks, the human brain-based model was the best at integrating helpful visual information to resolve auditory ambiguity.

Interestingly, compared to other models, the human brain-based model was particularly proficient at ignoring irrelevant audio stimuli that didn’t help to resolve ambiguities.

To test the impact of different anatomies of modulatory feedback, we compared the performance of a model based on human anatomy with identically sized models with different configurations of feedback/feedforward connectivity.

Each brain region is a recurrent convolutional network, and can receive two different types of input: driving feedforward and modulatory feedback. With this code, users can input macroscopic connectivity to build anatomically constrained DNNs.

What does it mean to have “biologically-inspired top-down feedback”? In the brain, feedback does not drive pyramidal neurons directly, but it modulates the feedforward signal (both multiplicatively and additively), as described in Larkum et al 2004.