New PNAS paper using CNN emergent attention mechanisms to identify new neuron types

Covert attention refers to the selection of part of the visual scene without moving our eyes.  Imagine you’re driving on a busy highway. While your eyes are fixed on the car ahead, you’re simultaneously tracking the movement of other vehicles in your peripheral vision. Or consider a social gathering where you discreetly pay attention to someone’s conversation without making direct eye contact.   When attention is directed to a location, people's performance in detecting an object is more accurate and faster.  Traditionally, scientists have studied how 

But a recent study turns this long-held assumption on its head. Researchers discovered that a simple artificial intelligence, given a basic task and no instructions about attention, spontaneously developed the same behavioral signatures. The findings suggest that this remarkable cognitive ability may not be so special after all.

1. Attention Isn't as "Advanced" as We Thought—It's an Emergent Skill

The most counter-intuitive finding is that covert attention appears to be an "emergent form of intelligence." Rather than being a pre-programmed module unique to complex brains, it arises naturally when a system is simply optimized to perform a task more efficiently.

This new perspective is supported by growing evidence from the animal kingdom. The behavioral signs of covert attention have been found in a wide range of animals, including crows, rodents, archer fish, and even bees—creatures that lack the mammalian brain structure—specifically, the parietal lobes in the neocortex—previously thought to be required for this function. This widespread presence hinted that a simpler, more fundamental principle was at play.

Professor Miguel Eckstein, a lead researcher on the study, highlights this shift in thinking:

“To some extent, people thought this covert attention business was something of humans, of primates, and that was it... But as years have gone by, the behavioral signatures of covert attention have been shown in animals, such as crows, rodents, archer fish, and even bees. So that motivated us to think that there must be something simpler that gives rise to these effects.”

2. An AI Taught Itself to "Pay Attention" Without Any Instructions

To test their hypothesis, researchers trained a standard convolutional neural network (CNN)—a type of AI model—on a straightforward task: detect a faint, tilted line hidden within a noisy image. Most of the time, a visual cue (a small box) appeared in the image, indicating the likely location of the target line.

Crucially, the CNN was never explicitly told what "attention" was, what the cue meant, or that it should prioritize information from the cued location. The model was only trained to get better at one thing: correctly detecting the target.

The result was astonishing. In the process of optimizing its performance, the network spontaneously developed human-like attentional behaviors. It became significantly faster and more accurate at finding the target when it appeared at the cued location, effectively demonstrating covert attention without ever being programmed for it. Its performance was so effective that it was comparable to a "Bayesian ideal observer"—a theoretical model that represents the highest possible accuracy for the task, despite the AI having none of the pre-programmed statistical knowledge the ideal observer is given.

3. The AI Predicted New Types of Brain Cells That Actually Exist

The discovery didn't stop there. Using neuroscience-style analytical tools, the scientists peered inside the 1.8 million "neurons" of the trained CNN to understand the internal mechanisms it had created.

The CNN predicted the existence of specific neuron types that neurophysiologists had not previously highlighted in attention research. These included "cue-inhibitory cells" (which diminish their response when a cue is present), "location-opponent cells" (which are excited by a stimulus in one location but inhibited by one in another), and neurons that "pool information across space."

We then went back the scientists went back and re-analyzed previous brain recordings from the superior colliculus in mice performing a similar attention task, they found evidence of these exact neuron types the AI had predicted. The model's internal workings provided a guide that revealed previously overlooked mechanisms in a real, biological brain.

4. Why we think this is important

This research pioneers a powerful methodological shift. Instead of treating AI models as inscrutable "black-box function approximators," scientists can now use them as analyzable "model systems," or what the paper calls an in silico preparation.

The benefit of this approach is immense. A relatively simple, fully observable AI can generate concrete, testable hypotheses about how vastly more complex biological neural circuits might function. The CNN acts as a guide, suggesting what neurophysiologists should look for in the billions of neurons that make up a living brain, accelerating the pace of discovery.

Conclusion: Rethinking Covert Attention

This study reshapes our understanding of a fundamental cognitive function. It suggests that complex abilities like covert attention may not be intricately designed, pre-programmed modules. Instead, they can be the natural, emergent result of a system simply optimizing its ability to process information and perform a task well.

This research transforms a simple AI from a mere tool into a collaborator in discovery. If a fundamental skill like attention can emerge from simple optimization, it forces us to ask: are memory, prediction, and even creativity just waiting to be unlocked by the right task, rather than a special, pre-built architecture?