Recurrent neural networks (RNNs) have yielded promising results for both recognizing objects in challenging conditions and modeling aspects of primate vision. However, the representational dynamics of recurrent computations remain poorly understood, especially in large-scale visual models. Here, we studied such dynamics in RNNs trained for object classification on MiniEcoset, a novel subset of ecoset. We report two main insights. First, upon inference, representations continued to evolve after correct classification, suggesting a lack of the notion of being ``done with classification''. Second, focusing on ``readout zones'' as a way to characterize the activation trajectories, we observe that misclassified representations exhibit activation patterns with lower L2 norm, and are positioned more peripherally in the readout zones. Such arrangements help the misclassified representations move into the correct zones as time progresses. Our findings generalize to networks with lateral and top-down connections, and include both additive and multiplicative interactions with the bottom-up sweep. The results therefore contribute to a general understanding of RNN dynamics in naturalistic tasks. We hope that the analysis framework will aid future investigations of other types of RNNs, including understanding of representational dynamics in primate vision.

翻译：循环神经网络（RNN）在复杂条件下的物体识别及灵长类视觉建模方面取得了显著进展。然而，循环计算中的表征动态仍鲜被深入理解，尤其是在大规模视觉模型中。本文研究了基于MiniEcoset（ecoset新型子集）训练进行物体分类的RNN中的此类动态。我们获得两项主要发现：第一，推理过程中，正确分类后表征仍持续演变，表明网络缺乏“分类完成”的概念；第二，通过聚焦“读出区域”以刻画激活轨迹，发现错误分类表征的激活模式具有更低L2范数，且在读出区域中位于更外围的位置。这种排列有助于错误分类表征随时间推移移入正确区域。上述发现可推广至具有侧向连接和自上而下连接的网络，涵盖与自底向上扫描的加性与乘性交互。因此，本研究为理解自然场景任务中RNN动态提供了普适性见解，期望该分析框架能助力未来对其他类型RNN的探索，包括灵长类视觉表征动态的研究。