Learning to Learn with Feedback and Local Plasticity

Abstract

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.

References in corpus (12)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Matching Networks for One Shot Learning
• Learning to reinforcement learn
• Using Fast Weights to Attend to the Recent Past
• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
• Two Routes to Scalable Credit Assignment without Weight Symmetry
• Spike-based causal inference for weight alignment