论文标题
圈子是前进的道路：复发在视觉推理中的作用
Going in circles is the way forward: the role of recurrence in visual inference
论文作者
论文摘要
生物视觉系统表现出丰富的复发连接性。相比之下，用于视觉识别的最先进的神经网络模型在很大程度上或仅取决于前馈计算。任何有限的复发性神经网络（RNN）都可以随时间张开，以产生等效的前馈神经网络（FNN）。这个重要的见解表明，计算神经科学家可能不需要进行经常性计算，并且计算机视觉工程师如果构建经常性模型，可能会将自己限制为FNN的特殊情况。相反，我们在这里争辩说，FNN是RNN的特殊情况，计算神经科学家和工程师应进行复发，以了解大脑和机器如何能够（1）实现更大，更灵活的计算深度，（2）将复杂的计算压缩为有限的硬件，（3）将预期的依赖性和数据限制为预期，并将优先级的依赖性和注意力集成为4（4）（4）（4）预测，（5）利用迭代计算的力量。
Biological visual systems exhibit abundant recurrent connectivity. State-of-the-art neural network models for visual recognition, by contrast, rely heavily or exclusively on feedforward computation. Any finite-time recurrent neural network (RNN) can be unrolled along time to yield an equivalent feedforward neural network (FNN). This important insight suggests that computational neuroscientists may not need to engage recurrent computation, and that computer-vision engineers may be limiting themselves to a special case of FNN if they build recurrent models. Here we argue, to the contrary, that FNNs are a special case of RNNs and that computational neuroscientists and engineers should engage recurrence to understand how brains and machines can (1) achieve greater and more flexible computational depth, (2) compress complex computations into limited hardware, (3) integrate priors and priorities into visual inference through expectation and attention, (4) exploit sequential dependencies in their data for better inference and prediction, and (5) leverage the power of iterative computation.
