Top-Down Network Combines Back-Propagation with Attention

Cortical processing, in vision and other domains, combines bottom-up (BU) with extensive top-down (TD) processing. Two primary goals attributed to TD processing are learning and directing attention. These two roles are accomplished in current network models through distinct mechanisms. Attention guidance is often implemented by extending the model's architecture, while learning is typically accomplished by an external learning algorithm such as back-propagation. In the current work, we present an integration of the two functions above, which appear unrelated, using a single unified mechanism inspired by the human brain. We propose a novel symmetric bottom-up top-down network structure that can integrate conventional bottom-up networks with a symmetric top-down counterpart, allowing each network to recurrently guide and influence the other. For example, during multi-task learning, the same top-down network is being used for both learning, via propagating feedback signals, and at the same time also for top-down attention, by guiding the bottom-up network to perform a selected task. In contrast with standard models, no external back-propagation is used for learning. Instead, we propose a 'Counter-Hebb' learning, which adjusts the weights of both the bottom-up and top-down networks simultaneously. We show that our method achieves competitive performance on standard multi-task learning benchmarks. Yet, unlike existing methods, we rely on single-task architectures and optimizers, without any task-specific parameters. The results, which show how attention-guided multi-tasks can be combined efficiently with internal learning in a unified TD process, suggest a possible model for combining BU and TD processing in human vision.