Visual curve tracing properties.

Jolicœur, Pierre; Ullman, Shimon; Mackay, Marilynn

doi:10.1037//0096-1523.17.4.997

Cited by 19 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, Marić & Domijan [ 63 , 64 ] configured a winner-take-all model to trace curves, also using separate feedforward and recurrent units. Their model could explain why tracing proceeds faster for target curves that are farther from a distractor curve than for target curves that are near a distractor, in accordance with psychophysical and neurophysiological data [ 18 , 65 ]. To propagate the enhanced activity, the model used a comparison between the activity levels of recurrent and feedforward units, whereas in the present model the activity propagation by recurrent units is gated by the feedforward units.…”

Section: Discussionmentioning

confidence: 59%

Recurrent neural networks that learn multi-step visual routines with reinforcement learning

Mollard,

Wacongne,

Bohte

et al. 2024

PLoS Comput Biol

View full text Add to dashboard Cite

Many cognitive problems can be decomposed into series of subproblems that are solved sequentially by the brain. When subproblems are solved, relevant intermediate results need to be stored by neurons and propagated to the next subproblem, until the overarching goal has been completed. We will here consider visual tasks, which can be decomposed into sequences of elemental visual operations. Experimental evidence suggests that intermediate results of the elemental operations are stored in working memory as an enhancement of neural activity in the visual cortex. The focus of enhanced activity is then available for subsequent operations to act upon. The main question at stake is how the elemental operations and their sequencing can emerge in neural networks that are trained with only rewards, in a reinforcement learning setting. We here propose a new recurrent neural network architecture that can learn composite visual tasks that require the application of successive elemental operations. Specifically, we selected three tasks for which electrophysiological recordings of monkeys’ visual cortex are available. To train the networks, we used RELEARNN, a biologically plausible four-factor Hebbian learning rule, which is local both in time and space. We report that networks learn elemental operations, such as contour grouping and visual search, and execute sequences of operations, solely based on the characteristics of the visual stimuli and the reward structure of a task. After training was completed, the activity of the units of the neural network elicited by behaviorally relevant image items was stronger than that elicited by irrelevant ones, just as has been observed in the visual cortex of monkeys solving the same tasks. Relevant information that needed to be exchanged between subroutines was maintained as a focus of enhanced activity and passed on to the subsequent subroutines. Our results demonstrate how a biologically plausible learning rule can train a recurrent neural network on multistep visual tasks.

show abstract