Recurrent computations for visual pattern completion
Making inferences from partial information constitutes a critical aspect of cognition. During visual perception, pattern completion enables recognition of poorly visible or occluded objects. We combined psychophysics, physiology and computational models to test the hypothesis that pattern completion is implemented by recurrent computations and present three pieces of evidence that are consistent with this hypothesis. First, subjects robustly recognized objects even when rendered <15% visible, but recognition was largely impaired when processing was interrupted by backward masking. Second, invasive physiological responses along the human ventral cortex exhibited visually selective responses to partially visible objects that were delayed compared to whole objects, suggesting the need for additional computations. These physiological delays were correlated with the effects of backward masking. Third, state-of-the-art feed-forward computational architectures were not robust to partial visibility. However, recognition performance was recovered when the model was augmented with attractor-based recurrent connectivity. These results provide a strong argument of plausibility for the role of recurrent computations in making visual inferences from partial information.
Code (1)
Tasks
Image ClassificationSimilar Papers 제목 키워드 기반
Visual hyperacuity with moving sensor and recurrent neural computations
Dynamical phenomena, such as recurrent neuronal activity and perpetual motion of the eye, are typically overlooked in models of bottom-up visual perception. Recent experiments suggest that tiny inter-saccadic eye motion…
Learning visual motion in recurrent neural networks
We present a dynamic nonlinear generative model for visual motion based on a latent representation of binary-gated Gaussian variables. Trained on sequences of images, the model learns to represent different movement dire…
Recurrent Memory Networks for Language Modeling
Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we pr…
Language ModelingLanguage ModellingSentenceSentence CompletionHow the brain might work: statistics flowing in redundant population codes
It is widely believed that the brain performs approximate probabilistic inference to estimate causal variables in the world from ambiguous sensory data. To understand these computations, we need to analyze how informatio…
Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items …
Collaborative FilteringMatrix CompletionRecommendation Systems