Interest in biologically inspired alternatives to backpropagation is driven by the desire to both advance connections between deep learning and neuroscience and address backpropagation's shortcomings on tasks such as online, continual learning. However, local synaptic learning rules like those employed by the brain have so far failed to match the performance of backpropagation in deep networks. In this study, we employ meta-learning to discover networks that learn using feedback connections and local, biologically inspired learning rules. Importantly, the feedback connections are not tied to the feedforward weights, avoiding biologically implausible weight transport. Our experiments show that meta-trained networks effectively use feedback connections to perform online credit assignment in multi-layer architectures. Surprisingly, this approach matches or exceeds a state-of-the-art gradient-based online meta-learning algorithm on regression and classification tasks, excelling in particular at continual learning. Analysis of the weight updates employed by these models reveals that they differ qualitatively from gradient descent in a way that reduces interference between updates. Our results suggest the existence of a class of biologically plausible learning mechanisms that not only match gradient descent-based learning, but also overcome its limitations.

Weaknesses: As pointed out before, one major advantage of their method is that during learning no backpropagation is required. The authors rightly mention that the same advantage applies to meta-learning in recurrent neural networks (e.g. Not of all their contributions are novel: 1. "We provide support for the idea that the credit assignment problem itself may be viewed as an optimization problem, amenable to solution via meta-learning." This has been shown many times before, e.g. This also has been shown many times before, e.g.

The reviewers seem to agree that there is value in proposed work. After a discussion, based on the rebuttal, the consensus is that given that the authors integrate in the camera ready the details of the rebuttal (particularly the comments of R4) and *toning down* or being more precise in the claims being made, I think this work would be very interesting and useful to the community. Please do take into account this advice, as it will help the work to have maximal impact in the community and to not be misinterpreted or its claims to be abused.

Interest in biologically inspired alternatives to backpropagation is driven by the desire to both advance connections between deep learning and neuroscience and address backpropagation's shortcomings on tasks such as online, continual learning. However, local synaptic learning rules like those employed by the brain have so far failed to match the performance of backpropagation in deep networks. In this study, we employ meta-learning to discover networks that learn using feedback connections and local, biologically inspired learning rules. Importantly, the feedback connections are not tied to the feedforward weights, avoiding biologically implausible weight transport. Our experiments show that meta-trained networks effectively use feedback connections to perform online credit assignment in multi-layer architectures.