Equilibrium Propagation (EP) is a biologically-inspired counterpart of Backpropagation Through Time (BPTT) which, owing to its strong theoretical guarantees and the locality in space of its learning rule, fosters the design of energy-efficient hardware dedicated to learning. In practice, however, EP does not scale to visual tasks harder than MNIST. In this work, we show that a bias in the gradient estimate of EP, inherent in the use of finite nudging, is responsible for this phenomenon and that cancelling it allows training deep ConvNets by EP, including architectures with distinct forward and backward connections. These results highlight EP as a scalable approach to compute error gradients in deep neural networks, thereby motivating its hardware implementation.

中文翻译：

---

通过大幅度减少其梯度估计偏差，将均衡传播扩展到深层卷积网络

均衡传播（EP）是生物学启发的时间反向传播（BPTT）的对应物，由于其强大的理论保证和学习规则在空间上的局限性，因此促进了致力于学习的节能硬件的设计。然而，实际上，EP不能比MNIST更难扩展到视觉任务。在这项工作中，我们证明了使用有限推力所固有的EP梯度估计中的偏差是造成这种现象的原因，并且消除它可以通过EP训练深层的ConvNet，包括具有明显前向和反向连接的体系结构。这些结果凸显了EP作为一种可扩展的方法来计算深度神经网络中的误差梯度，从而激发了其硬件实现。