Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers
arXiv:1902.10658 · doi:10.3390/e24010059
Abstract
Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the Minimum Description Length (MDL) principle. Treating the neural network optimization process as a partially observable model selection problem, the regularity normalization constrains the implicit space by a normalization factor, the universal code length. We compute this universal code incrementally across neural network layers and demonstrate the flexibility to include data priors such as top-down attention and other oracle information. Empirically, our approach outperforms existing normalization methods in tackling limited, imbalanced and non-stationary input distribution in image classification, classic control, procedurally-generated reinforcement learning, generative modeling, handwriting generation and question answering tasks with various neural network architectures. Lastly, the unsupervised attention mechanisms is a useful probing tool for neural networks by tracking the dependency and critical learning stages across layers and recurrent time steps of deep networks.
arXiv commentAccepted and to be published by Entropy. Codes at https://github.com/doerlbh/UnsupervisedAttentionMechanism
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Intriguing properties of neural networks
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- OpenAI Gym
- MINE: Mutual Information Neural Estimation
- Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
- The Price of Fair PCA: One Extra Dimension
- Biologically Inspired Mechanisms for Adversarial Robustness
- A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry