Recurrent circuits as multi-path ensembles for modeling responses of early visual cortical neurons

In this paper, we showed that adding within-layer recurrent connections to feed-forward neural network models could improve the performance of neural response prediction in early visual areas by up to 11 percent across different data sets and over tens of thousands of model configurations. To understand why recurrent models perform better, we propose that recurrent computation can be conceptualized as an ensemble of multiple feed-forward pathways of different lengths with shared parameters. By reformulating a recurrent model as a multi-path model and analyzing the recurrent model through its multi-path ensemble, we found that the recurrent model outperformed the corresponding feed-forward one due to the former's compact and implicit multi-path ensemble that allows approximating the complex function underlying recurrent biological circuits with efficiency. In addition, we found that the performance differences among recurrent models were highly correlated with the differences in their multi-path ensembles in terms of path lengths and path diversity; a balance of paths of different lengths in the ensemble was necessary for the model to achieve the best performance. Our studies shed light on the computational rationales and advantages of recurrent circuits for neural modeling and machine learning tasks in general.

Recurrent Feedback Improves Feedforward Representations in Deep Neural Networks

The abundant recurrent horizontal and feedback connections in the primate visual cortex are thought to play an important role in bringing global and semantic contextual information to early visual areas during perceptual inference, helping to resolve local ambiguity and fill in missing details. In this study, we find that introducing feedback loops and horizontal recurrent connections to a deep convolution neural network (VGG16) allows the network to become more robust against noise and occlusion during inference, even in the initial feedforward pass. This suggests that recurrent feedback and contextual modulation transform the feedforward representations of the network in a meaningful and interesting way. We study the population codes of neurons in the network, before and after learning with feedback, and find that learning with feedback yielded an increase in discriminability (measured by d-prime) between the different object classes in the population codes of the neurons in the feedforward path, even at the earliest layer that receives feedback. We find that recurrent feedback, by injecting top-down semantic meaning to the population activities, helps the network learn better feedforward paths to robustly map noisy image patches to the latent representations corresponding to important visual concepts of each object class, resulting in greater robustness of the network against noises and occlusion as well as better fine-grained recognition.