A Novel Predictive-Coding-Inspired Variational RNN Model for Online Prediction and Recognition

@article{Ahmadi2019ANP,
  title={A Novel Predictive-Coding-Inspired Variational RNN Model for Online Prediction and Recognition},
  author={Ahmadreza Ahmadi and Jun Tani},
  journal={Neural Computation},
  year={2019},
  volume={31},
  pages={2025-2074}
}
This study introduces PV-RNN, a novel variational RNN inspired by predictive-coding ideas. The model learns to extract the probabilistic structures hidden in fluctuating temporal patterns by dynamically changing the stochasticity of its latent states. Its architecture attempts to address two major concerns of variational Bayes RNNs: how latent variables can learn meaningful representations and how the inference model can transfer future observations to the latent variables. PV-RNN does both by… 
Balancing Active Inference and Active Learning with Deep Variational Predictive Coding for EEG
  • André Ofner, S. Stober
  • Computer Science
    2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
  • 2020
TLDR
A hierarchical probabilistic network that minimises prediction error at multiple levels of spatio-temporal abstraction is introduced that enables dynamic inference of the current context using the learned generative model.
Predictive coding, precision and natural gradients
TLDR
It is shown that hierarchical predictive coding networks with learnable precision indeed are able to solve various supervised and unsupervised learning tasks with performance comparable to global backpropagation with natural gradients and outperform their classical gradient descent counterpart on tasks where high amounts of noise are embedded in data or label inputs.
Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network
TLDR
The current study shows that the predictive coding and active inference frameworks, which employ a generative model, can develop better generalization by learning a prior distribution in a low dimensional latent state space representing probabilistic structures extracted from well habituated sensory-motor trajectories.
PreCNet: Next Frame Video Prediction Based on Predictive Coding
TLDR
This work transforms the seminal model of Rao and Ballard (1999) into a modern deep learning framework while remaining maximally faithful to the original schema, and demonstrates that an architecture carefully based in a neuroscience model, without being explicitly tailored to the task at hand, can exhibit unprecedented performance.
Reverse-Engineering Neural Networks to Characterize Their Cost Functions
TLDR
This letter considers a class of biologically plausible cost functions for neural networks, where the same cost function is minimized by both neural activity and plasticity, and establishes the formal equivalence between neural network cost functions and variational free energy under some prior beliefs about latent states that generate inputs.
Variational Recurrent Models for Solving Partially Observable Control Tasks
TLDR
The experiments show that the proposed RL algorithm achieved better data efficiency and/or learned more optimal policy than other alternative approaches in tasks in which unobserved states cannot be inferred from raw observations in a simple manner.
Micro-supervised Disturbance Learning: A Perspective of Representation Probability Distribution
TLDR
A deep Micro-supervised Disturbance Learning (Micro-DL) framework based on the Micro-DGRBM and Micro-DRBM models is presented and shown to show better performance in comparison to the baseline method, the most related shallow models and deep frameworks for clustering.
Initialization of Latent Space Coordinates via Random Linear Projections for Learning Robotic Sensory-Motor Sequences
TLDR
Motivated by results of embedding theory, in particular, generalizations of Whitney embedding theorem, it is shown that random linear projection of motor sequences into low dimensional space loses very little information about structure of kinematics data.
Minor Constraint Disturbances for Deep Semi-supervised Learning
TLDR
A novel Minor Constraint Disturbances-based Deep Semi-supervised Feature Learning framework (MCD-DSFL) from the perspective of probability distribution for feature representation that significantly reduces the reliance on the labels and improves the stability of the semi- supervised feature learning in high-dimensional space simultaneously.
...
...

References

SHOWING 1-10 OF 82 REFERENCES
Z-Forcing: Training Stochastic Recurrent Networks
TLDR
This work unify successful ideas from recently proposed architectures into a stochastic recurrent model that achieves state-of-the-art results on standard speech benchmarks such as TIMIT and Blizzard and competitive performance on sequential MNIST.
Learning to Reproduce Fluctuating Time Series by Inferring Their Time-Dependent Stochastic Properties: Application in Robot Learning Via Tutoring
TLDR
It was shown that a humanoid robot using the proposed network can learn to reproduce latent stochastic structures hidden in fluctuating tutoring trajectories and this learning scheme is essential for the acquisition of sensory-guided skilled behavior.
Auto-Encoding Variational Bayes
TLDR
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Bridging the Gap Between Probabilistic and Deterministic Models: A Simulation Study on a Variational Bayes Predictive Coding Recurrent Neural Network Model
TLDR
A novel variational Bayes predictive coding RNN model, which can learn to generate fluctuated temporal patterns from exemplars, is proposed, which learns to maximize the lower bound of the weighted sum of the regularization and reconstruction error terms.
Generating Sentences from a Continuous Space
TLDR
This work introduces and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences that allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features.
Representation Learning: A Review and New Perspectives
TLDR
Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.
Sequential Neural Models with Stochastic Layers
TLDR
Stochastic recurrent neural networks are introduced which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model.
Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
TLDR
Deep Variational Bayes Filters is introduced, a new method for unsupervised learning and identification of latent Markovian state space models that can overcome intractable inference distributions via variational inference and enables realistic long-term prediction.
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
TLDR
This work presents a novel framework based on conditional variational autoencoders that capture the discourse-level diversity in the encoder and uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders.
Variational Lossy Autoencoder
TLDR
This paper presents a simple but principled method to learn global representations by combining Variational Autoencoder (VAE) with neural autoregressive models such as RNN, MADE and PixelRNN/CNN with greatly improve generative modeling performance of VAEs.
...
...