The error-backpropagation (backprop) algorithm remains the most common solution to the credit assignment problem in artificial neural networks. In neuroscience, it is unclear whether the brain could adopt a similar strategy to correctly modify its synapses. Recent models have attempted to bridge this gap while being consistent with a range of experimental observations. However, these models are either unable to effectively backpropagate error signals across multiple layers or require a multi-phase learning process, neither of which are reminiscent of learning in the brain. Here, we introduce a new model, bursting cortico-cortical networks (BurstCCN), which solves these issues by integrating known properties of cortical networks namely bursting activity, short-term plasticity (STP) and dendrite-targeting interneurons. BurstCCN relies on burst multiplexing via connection-type-specific STP to propagate backprop-like error signals within deep cortical networks. These error signals are encoded at distal dendrites and induce burst-dependent plasticity as a result of excitatory-inhibitory topdown inputs. First, we demonstrate that our model can effectively backpropagate errors through multiple layers using a single-phase learning process. Next, we show both empirically and analytically that learning in our model approximates backprop-derived gradients. Finally, we demonstrate that our model is capable of learning complex image classification tasks (MNIST and CIFAR-10). Overall, our results suggest that cortical features across sub-cellular, cellular, microcircuit and systems levels jointly underlie single-phase efficient deep learning in the brain.
翻译:错误背对映算法仍然是人工神经网络中信用分配问题最常见的解决办法。 在神经科学中, 大脑能否采用类似的策略来正确修改其神经突触, 尚不清楚。 最近的模型试图弥补这一差距, 同时又与一系列实验观测保持一致 。 但是, 这些模型要么无法有效地反映跨多层的错误信号, 或者需要多阶段学习过程, 而这些模式都不是大脑学习的回溯性。 在这里, 我们引入了一个新的模型, 爆发的皮层- 皮层网络( BurstCCN ), 通过整合已知的皮层网络特性来解决这些问题, 包括爆裂活动、 短期塑料(STP) 和 dendrend- 瞄准内中中子。 勃斯特CCN 依靠通过连接类型特定的 STP 来传播反向反向偏差的错误信号, 而在深层的脑部网络中, 这些错误信号被解析, 并诱导出我们内部的直线结构, 通过模型解析分析结果, 显示我们内部的深度分析过程 。