论文标题
持续学习使用路由路由的卷积神经网络
Continual learning using hash-routed convolutional neural networks
论文作者
论文摘要
持续的学习可能会将机器学习范式从以数据为中心转移到以模型为中心。持续学习模型需要有效地扩展以处理语义上不同的数据集，同时避免不必要的增长。我们介绍了哈希路由的卷积神经网络：一组数据动态流动的卷积单元。使用功能哈希比较特征地图，并将类似的数据路由到同一单元。哈希路由网络由于其路由性质提供了出色的可塑性，同时通过使用正交功能哈希产生稳定的功能。每个单元分开演变，可以添加新单元（仅在必要时才使用）。哈希路由网络在各种典型的持续学习基准测试中取得了出色的性能，而无需存储原始数据并仅使用梯度下降训练。除了为受到令人鼓舞的结果提供持续的监督任务学习框架外，我们的模型还可以用于无监督或强化学习。
Continual learning could shift the machine learning paradigm from data centric to model centric. A continual learning model needs to scale efficiently to handle semantically different datasets, while avoiding unnecessary growth. We introduce hash-routed convolutional neural networks: a group of convolutional units where data flows dynamically. Feature maps are compared using feature hashing and similar data is routed to the same units. A hash-routed network provides excellent plasticity thanks to its routed nature, while generating stable features through the use of orthogonal feature hashing. Each unit evolves separately and new units can be added (to be used only when necessary). Hash-routed networks achieve excellent performance across a variety of typical continual learning benchmarks without storing raw data and train using only gradient descent. Besides providing a continual learning framework for supervised tasks with encouraging results, our model can be used for unsupervised or reinforcement learning.
