Imagine two artists painting the same subject, using different techniques but still creating similar masterpieces. Similarly, deep neural networks (DNNs) are like the artists’ tools, capable of modeling human cognition and producing behaviors similar to those of the brain. However, scientists are now questioning the degree of algorithmic equivalence between the brain and DNNs. They examine three levels of similarity: first, behavioral/brain responses; second, processed stimulus features; and finally, the algorithms themselves. By doing so, they aim to uncover whether the algorithms used by DNNs align with those employed by our brains. The findings could have profound implications for understanding the nature of cognition and developing more brain-inspired AI models. To dive deeper into this fascinating research, check out the full article!

Deep neural networks (DNNs) have become powerful and increasingly ubiquitous tools to model human cognition, and often produce similar behaviors. For example, with their hierarchical, brain-inspired organization of computations, DNNs apparently categorize real-world images in the same way as humans do. Does this imply that their categorization algorithms are also similar? We have framed the question with three embedded degrees that progressively constrain algorithmic similarity evaluations: equivalence of (i) behavioral/brain responses, which is current practice, (ii) the stimulus features that are processed to produce these outcomes, which is more constraining, and (iii) the algorithms that process these shared features, the ultimate goal.

Read Full Article (External Site)