Bridging the Gap between Probabilistic and Deterministic Models: A Simulation Study on a Variational Bayes Predictive Coding Recurrent Neural Network Model
This work addresses the gap between probabilistic and deterministic models in neural networks, with potential implications for understanding neuronal mechanisms in autism spectrum disorder and free action, but it appears incremental as it builds on existing variational and predictive coding methods.
The paper tackled the challenge of generating fluctuated temporal patterns by proposing a variational Bayes predictive coding RNN model, with simulation results showing that strong weighting of reconstruction leads to deterministic chaos and strong weighting of regularization leads to stochastic dynamics, while generalized learning occurs between these extremes.
The current paper proposes a novel variational Bayes predictive coding RNN model, which can learn to generate fluctuated temporal patterns from exemplars. The model learns to maximize the lower bound of the weighted sum of the regularization and reconstruction error terms. We examined how this weighting can affect development of different types of information processing while learning fluctuated temporal patterns. Simulation results show that strong weighting of the reconstruction term causes the development of deterministic chaos for imitating the randomness observed in target sequences, while strong weighting of the regularization term causes the development of stochastic dynamics imitating probabilistic processes observed in targets. Moreover, results indicate that the most generalized learning emerges between these two extremes. The paper concludes with implications in terms of the underlying neuronal mechanisms for autism spectrum disorder and for free action.