Learning Sequence Attractors in Recurrent Networks with Hidden Neurons

• URL: http://arxiv.org/abs/2404.02729v1
• Date: Wed, 3 Apr 2024 13:29:12 GMT
• Title: Learning Sequence Attractors in Recurrent Networks with Hidden Neurons
• Authors: Yao Lu, Si Wu,
• Abstract summary: We show that to store arbitrary pattern sequences, it is necessary for the network to include hidden neurons. We develop a local learning algorithm to learn sequence attractors in the networks with hidden neurons. We demonstrate that the network model can store and retrieve sequences robustly on synthetic and real-world datasets.
• Score: 8.639486652067024
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The brain is targeted for processing temporal sequence information. It remains largely unclear how the brain learns to store and retrieve sequence memories. Here, we study how recurrent networks of binary neurons learn sequence attractors to store predefined pattern sequences and retrieve them robustly. We show that to store arbitrary pattern sequences, it is necessary for the network to include hidden neurons even though their role in displaying sequence memories is indirect. We develop a local learning algorithm to learn sequence attractors in the networks with hidden neurons. The algorithm is proven to converge and lead to sequence attractors. We demonstrate that the network model can store and retrieve sequences robustly on synthetic and real-world datasets. We hope that this study provides new insights in understanding sequence memory and temporal information processing in the brain.

Related papers

• Sequential Learning in the Dense Associative Memory [1.2289361708127877]
  We investigate the performance of the Dense Associative Memory in sequential learning problems. We show that existing sequential learning methods can be applied to the Dense Associative Memory to improve sequential learning performance.
  arXiv  Detail & Related papers  (2024-09-24T04:23:00Z)
• Measures of Information Reflect Memorization Patterns [53.71420125627608]
  We show that the diversity in the activation patterns of different neurons is reflective of model generalization and memorization. Importantly, we discover that information organization points to the two forms of memorization, even for neural activations computed on unlabelled in-distribution examples.
  arXiv  Detail & Related papers  (2022-10-17T20:15:24Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Learning and Generalization in RNNs [11.107204912245841]
  We prove that simple recurrent neural networks can learn functions of sequences. New ideas enable us to extract information from the hidden state of the RNN in our proofs.
  arXiv  Detail & Related papers  (2021-05-31T18:27:51Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Ensemble perspective for understanding temporal credit assignment [1.9843222704723809]
  We show that each individual connection in recurrent neural networks is modeled by a spike and slab distribution, rather than a precise weight value. Our model reveals important connections that determine the overall performance of the network. It is thus promising to study the temporal credit assignment in recurrent neural networks from the ensemble perspective.
  arXiv  Detail & Related papers  (2021-02-07T08:14:05Z)
• Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory [79.42778415729475]
  We propose a novel incrementally trained recurrent architecture targeting explicitly multi-scale learning. We show how to extend the architecture of a simple RNN by separating its hidden state into different modules. We discuss a training algorithm where new modules are iteratively added to the model to learn progressively longer dependencies.
  arXiv  Detail & Related papers  (2020-06-29T08:35:49Z)
• Towards a Neural Model for Serial Order in Frontal Cortex: a Brain Theory from Memory Development to Higher-Level Cognition [53.816853325427424]
  We propose that the immature prefrontal cortex (PFC) use its primary functionality of detecting hierarchical patterns in temporal signals. Our hypothesis is that the PFC detects the hierarchical structure in temporal sequences in the form of ordinal patterns and use them to index information hierarchically in different parts of the brain. By doing so, it gives the tools to the language-ready brain for manipulating abstract knowledge and planning temporally ordered information.
  arXiv  Detail & Related papers  (2020-05-22T14:29:51Z)
• Encoding-based Memory Modules for Recurrent Neural Networks [79.42778415729475]
  We study the memorization subtask from the point of view of the design and training of recurrent neural networks. We propose a new model, the Linear Memory Network, which features an encoding-based memorization component built with a linear autoencoder for sequences.
  arXiv  Detail & Related papers  (2020-01-31T11:14:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.