Improved Robustness and Hyperparameter Selection in the Dense Associative Memory

• URL: http://arxiv.org/abs/2407.08742v4
• Date: Sat, 21 Sep 2024 12:25:24 GMT
• Title: Improved Robustness and Hyperparameter Selection in the Dense Associative Memory
• Authors: Hayden McAlister, Anthony Robins, Lech Szymanski,
• Abstract summary: The Dense Associative Memory generalizes the Hopfield network by allowing for sharper interaction functions. However, the implementation of the network relies on applying large exponents to the dot product of memory vectors and probe vectors. We describe the computational issues in detail, modify the original network description to mitigate the problem, and show the modification will not alter the networks' dynamics.
• Score: 1.2289361708127877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Dense Associative Memory generalizes the Hopfield network by allowing for sharper interaction functions. This increases the capacity of the network as an autoassociative memory as nearby learned attractors will not interfere with one another. However, the implementation of the network relies on applying large exponents to the dot product of memory vectors and probe vectors. If the dimension of the data is large the calculation can be very large and result in imprecisions and overflow when using floating point numbers in a practical implementation. We describe the computational issues in detail, modify the original network description to mitigate the problem, and show the modification will not alter the networks' dynamics during update or training. We also show our modification greatly improves hyperparameter selection for the Dense Associative Memory, removing dependence on the interaction vertex and resulting in an optimal region of hyperparameters that does not significantly change with the interaction vertex as it does in the original network.

Related papers

• Dense Associative Memory Through the Lens of Random Features [48.17520168244209]
  Dense Associative Memories are high storage capacity variants of the Hopfield networks. We show that this novel network closely approximates the energy function and dynamics of conventional Dense Associative Memories.
  arXiv  Detail & Related papers  (2024-10-31T17:10:57Z)
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks [63.35819388164267]
  We present a framework to tackle the memory explosion problem using memory replay techniques. PDGNNs with Topology-aware Embedding Memory (TEM) significantly outperform state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-01-24T03:03:17Z)
• Non-Separable Multi-Dimensional Network Flows for Visual Computing [62.50191141358778]
  We propose a novel formalism for non-separable multi-dimensional network flows. Since the flow is defined on a per-dimension basis, the maximizing flow automatically chooses the best matching feature dimensions. As a proof of concept, we apply our formalism to the multi-object tracking problem and demonstrate that our approach outperforms scalar formulations on the MOT16 benchmark in terms of robustness to noise.
  arXiv  Detail & Related papers  (2023-05-15T13:21:44Z)
• Enhancing ResNet Image Classification Performance by using Parameterized Hypercomplex Multiplication [1.370633147306388]
  This paper studies ResNet architectures and incorporates parameterized hypercomplex multiplication into the backend of residual, quaternion, and vectormap convolutional neural networks to assess the effect. We show that PHM does improve classification accuracy performance on several image datasets, including small, low-resolution CIFAR 10/100 and large high-resolution ImageNet and ASL, and can achieve state-of-the-art accuracy for hypercomplex networks.
  arXiv  Detail & Related papers  (2023-01-11T18:24:07Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented Networks [6.03025980398201]
  Memory-augmented neural networks enhance a neural network with an external key-value memory. We propose a generalized key-value memory that decouples its dimension from the number of support vectors. We show that adapting this parameter on demand effectively mitigates up to 44% nonidealities, at equal accuracy and number of devices.
  arXiv  Detail & Related papers  (2022-03-11T19:59:43Z)
• Non-Gradient Manifold Neural Network [79.44066256794187]
  Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent. We propose a novel manifold neural network based on non-gradient optimization.
  arXiv  Detail & Related papers  (2021-06-15T06:39:13Z)
• Robust High-dimensional Memory-augmented Neural Networks [13.82206983716435]
  Memory-augmented neural networks enhance neural networks with an explicit memory to overcome these issues. Access to this explicit memory occurs via soft read and write operations involving every individual memory entry. We propose a robust architecture that employs a computational memory unit as the explicit memory performing analog in-memory computation on high-dimensional (HD) vectors.
  arXiv  Detail & Related papers  (2020-10-05T12:01:56Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Improving Memory Utilization in Convolutional Neural Network Accelerators [16.340620299847384]
  We propose a mapping method that allows activation layers to overlap and thus utilize the memory more efficiently. Experiments with various real-world object detector networks show that the proposed mapping technique can decrease the activations memory by up to 32.9%. For higher resolution de-noising networks, we achieve activation memory savings of 48.8%.
  arXiv  Detail & Related papers  (2020-07-20T09:34:36Z)
• On Power Laws in Deep Ensembles [12.739425443572202]
  We show that one large network may perform worse than an ensemble of several medium-size networks with the same total number of parameters. Using the detected power law-like dependencies, we can predict the possible gain from the ensembling of networks with given structure.
  arXiv  Detail & Related papers  (2020-07-16T17:35:32Z)

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.