Maelstrom Networks

• URL: http://arxiv.org/abs/2408.16632v1
• Date: Thu, 29 Aug 2024 15:39:04 GMT
• Title: Maelstrom Networks
• Authors: Matthew Evanusa, Cornelia Fermüller, Yiannis Aloimonos,
• Abstract summary: We offer an alternative paradigm that combines the strength of recurrent networks, with the pattern matching capability of feed-forward neural networks. This allows the network to leverage the strength of feed-forward training without unrolling the network. It endows a neural network with a sequential memory that takes advantage of the inductive bias that data is organized causally in the temporal domain.
• Score: 19.33916380545711
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Artificial Neural Networks has struggled to devise a way to incorporate working memory into neural networks. While the ``long term'' memory can be seen as the learned weights, the working memory consists likely more of dynamical activity, that is missing from feed-forward models. Current state of the art models such as transformers tend to ``solve'' this by ignoring working memory entirely and simply process the sequence as an entire piece of data; however this means the network cannot process the sequence in an online fashion, and leads to an immense explosion in memory requirements. Here, inspired by a combination of controls, reservoir computing, deep learning, and recurrent neural networks, we offer an alternative paradigm that combines the strength of recurrent networks, with the pattern matching capability of feed-forward neural networks, which we call the \textit{Maelstrom Networks} paradigm. This paradigm leaves the recurrent component - the \textit{Maelstrom} - unlearned, and offloads the learning to a powerful feed-forward network. This allows the network to leverage the strength of feed-forward training without unrolling the network, and allows for the memory to be implemented in new neuromorphic hardware. It endows a neural network with a sequential memory that takes advantage of the inductive bias that data is organized causally in the temporal domain, and imbues the network with a state that represents the agent's ``self'', moving through the environment. This could also lead the way to continual learning, with the network modularized and ``'protected'' from overwrites that come with new data. In addition to aiding in solving these performance problems that plague current non-temporal deep networks, this also could finally lead towards endowing artificial networks with a sense of ``self''.

Related papers

• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Message Passing Variational Autoregressive Network for Solving Intractable Ising Models [6.261096199903392]
  Many deep neural networks have been used to solve Ising models, including autoregressive neural networks, convolutional neural networks, recurrent neural networks, and graph neural networks. Here we propose a variational autoregressive architecture with a message passing mechanism, which can effectively utilize the interactions between spin variables. The new network trained under an annealing framework outperforms existing methods in solving several prototypical Ising spin Hamiltonians, especially for larger spin systems at low temperatures.
  arXiv  Detail & Related papers  (2024-04-09T11:27:07Z)
• Expanding memory in recurrent spiking networks [2.8237889121096034]
  Recurrent spiking neural networks (RSNNs) are notoriously difficult to train because of the vanishing gradient problem that is enhanced by the binary nature of the spikes. We present a novel spiking neural network that circumvents these limitations.
  arXiv  Detail & Related papers  (2023-10-29T16:46:26Z)
• Spike-based computation using classical recurrent neural networks [1.9171404264679484]
  Spiking neural networks are artificial neural networks in which communication between neurons is only made of events, also called spikes. We modify the dynamics of a well-known, easily trainable type of recurrent neural network to make it event-based. We show that this new network can achieve performance comparable to other types of spiking networks in the MNIST benchmark.
  arXiv  Detail & Related papers  (2023-06-06T12:19:12Z)
• Spiking neural network for nonlinear regression [68.8204255655161]
  Spiking neural networks carry the potential for a massive reduction in memory and energy consumption. They introduce temporal and neuronal sparsity, which can be exploited by next-generation neuromorphic hardware. A framework for regression using spiking neural networks is proposed.
  arXiv  Detail & Related papers  (2022-10-06T13:04:45Z)
• Memory via Temporal Delays in weightless Spiking Neural Network [0.08399688944263842]
  We present a prototype for weightless spiking neural networks that can perform a simple classification task. The memory in this network is stored in the timing between neurons, rather than the strength of the connection.
  arXiv  Detail & Related papers  (2022-02-15T02:09:33Z)
• Artificial Neural Networks generated by Low Discrepancy Sequences [59.51653996175648]
  We generate artificial neural networks as random walks on a dense network graph. Such networks can be trained sparse from scratch, avoiding the expensive procedure of training a dense network and compressing it afterwards. We demonstrate that the artificial neural networks generated by low discrepancy sequences can achieve an accuracy within reach of their dense counterparts at a much lower computational complexity.
  arXiv  Detail & Related papers  (2021-03-05T08:45:43Z)
• Implicit recurrent networks: A novel approach to stationary input processing with recurrent neural networks in deep learning [0.0]
  In this work, we introduce and test a novel implementation of recurrent neural networks into deep learning. We provide an algorithm which implements the backpropagation algorithm on a implicit implementation of recurrent networks. A single-layer implicit recurrent network is able to solve the XOR problem, while a feed-forward network with monotonically increasing activation function fails at this task.
  arXiv  Detail & Related papers  (2020-10-20T18:55:32Z)
• Reservoir Memory Machines as Neural Computers [70.5993855765376]
  Differentiable neural computers extend artificial neural networks with an explicit memory without interference. We achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently.
  arXiv  Detail & Related papers  (2020-09-14T12:01:30Z)
• 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)
• 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.