Continuous Learning in a Hierarchical Multiscale Neural Network
2018pp. 1–7
Citations Over Time
Abstract
We reformulate the problem of encoding a multi-scale representation of a sequence in a language model by casting it in a continuous learning framework. We propose a hierarchical multi-scale language model in which short time-scale dependencies are encoded in the hidden state of a lower-level recurrent neural network while longer time-scale dependencies are encoded in the dynamic of the lower-level network by having a meta-learner update the weights of the lower-level neural network in an online meta-learning fashion. We use elastic weights consolidation as a higher-level to prevent catastrophic forgetting in our continuous learning framework.
Related Papers
- → Deep associative learning for neural networks(2021)12 cited
- → Scaling in a hierarchical unsupervised network(1999)3 cited
- → Towards Understanding Hierarchical Learning: Benefits of Neural Representations(2020)9 cited
- → Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks(2016)