论文标题
何时，何处以及如何向ANN添加新神经元
When, where, and how to add new neurons to ANNs
论文作者
论文摘要
即使与其他形式的结构学习（如修剪）相比，ANN中的神经发生是一个研究且困难的问题。通过将其分解为触发器和初始化，我们引入了一个研究神经发生各个方面的框架：在学习过程中何时，何地以及如何添加神经元。我们介绍了神经发生策略的神经正交性（North*）套件，基于激活或权重的正交性，将层的触发器和初始化结合起来，以动态增长融合到有效尺寸的性能网络。我们评估了对各种监督学习任务中其他最新神经发生作品的贡献。
Neurogenesis in ANNs is an understudied and difficult problem, even compared to other forms of structural learning like pruning. By decomposing it into triggers and initializations, we introduce a framework for studying the various facets of neurogenesis: when, where, and how to add neurons during the learning process. We present the Neural Orthogonality (NORTH*) suite of neurogenesis strategies, combining layer-wise triggers and initializations based on the orthogonality of activations or weights to dynamically grow performant networks that converge to an efficient size. We evaluate our contributions against other recent neurogenesis works across a variety of supervised learning tasks.
