Digital implementations of deep feature extractors are intrinsically informative

• URL: http://arxiv.org/abs/2502.15004v2
• Date: Thu, 03 Apr 2025 21:12:56 GMT
• Title: Digital implementations of deep feature extractors are intrinsically informative
• Authors: Max Getter,
• Abstract summary: We prove an upper bound for the speed of energy propagation in a unified framework.<n>We show global exponential energy decay for a range of 1) feature extractors with discrete-domain input signals, and 2) convolutional neural networks (CNNs) via scattering.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Rapid information (energy) propagation in deep feature extractors is crucial to balance computational complexity versus expressiveness as a representation of the input. We prove an upper bound for the speed of energy propagation in a unified framework that covers different neural network models, both over Euclidean and non-Euclidean domains. Additional structural information about the signal domain can be used to explicitly determine or improve the rate of decay. To illustrate this, we show global exponential energy decay for a range of 1) feature extractors with discrete-domain input signals, and 2) convolutional neural networks (CNNs) via scattering over locally compact abelian (LCA) groups.

Related papers

• Expanding-and-Shrinking Binary Neural Networks [3.6593289731343246]
  We propose the expanding-and-shrinking operation, which enhances binary feature maps with negligible increase of complexity. Our approach generalizes well across diverse applications ranging from image classification, object detection to generative diffusion model.
  arXiv  Detail & Related papers  (2025-03-31T04:13:33Z)
• Neuromorphic Wireless Split Computing with Multi-Level Spikes [69.73249913506042]
  Neuromorphic computing uses spiking neural networks (SNNs) to perform inference tasks. embedding a small payload within each spike exchanged between spiking neurons can enhance inference accuracy without increasing energy consumption. split computing - where an SNN is partitioned across two devices - is a promising solution. This paper presents the first comprehensive study of a neuromorphic wireless split computing architecture that employs multi-level SNNs.
  arXiv  Detail & Related papers  (2024-11-07T14:08:35Z)
• Scalable spectral representations for multi-agent reinforcement learning in network MDPs [13.782868855372774]
  A popular model for multi-agent control, Network Markov Decision Processes (MDPs) pose a significant challenge to efficient learning. We first derive scalable spectral local representations for network MDPs, which induces a network linear subspace for the local $Q$-function of each agent. We design a scalable algorithmic framework for continuous state-action network MDPs, and provide end-to-end guarantees for the convergence of our algorithm.
  arXiv  Detail & Related papers  (2024-10-22T17:45:45Z)
• Spectral Informed Neural Network: An Efficient and Low-Memory PINN [3.8534287291074354]
  We propose a spectral-based neural network that substitutes the differential operator with a multiplication. Compared to the PINNs, our approach requires lower memory and shorter training time. We provide two strategies to train networks by their spectral information.
  arXiv  Detail & Related papers  (2024-08-29T10:21:00Z)
• Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks [1.5124439914522694]
  We introduce a theoretical framework that explains the capacity property of sinusoidal networks. We show how its layer compositions produce a large number of new frequencies expressed as integer combinations of the input frequencies. Our method, referred to as TUNER, greatly improves the stability and convergence of sinusoidal INR training, leading to detailed reconstructions.
  arXiv  Detail & Related papers  (2024-07-30T18:24:46Z)
• Spectral complexity of deep neural networks [2.099922236065961]
  We use the angular power spectrum of the limiting field to characterize the complexity of the network architecture.<n>On this basis, we classify neural networks as low-disorder, sparse, or high-disorder.<n>We show how this classification highlights a number of distinct features for standard activation functions, and in particular, sparsity properties of ReLU networks.
  arXiv  Detail & Related papers  (2024-05-15T17:55:05Z)
• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• Locality-Aware Generalizable Implicit Neural Representation [54.93702310461174]
  Generalizable implicit neural representation (INR) enables a single continuous function to represent multiple data instances. We propose a novel framework for generalizable INR that combines a transformer encoder with a locality-aware INR decoder. Our framework significantly outperforms previous generalizable INRs and validates the usefulness of the locality-aware latents for downstream tasks.
  arXiv  Detail & Related papers  (2023-10-09T11:26:58Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks [56.084798078072396]
  We take a step towards closing the gap between theory and practice by significantly improving the known theoretical bounds on both the network width and the convergence time. We show that convergence to a global minimum is guaranteed for networks with quadratic widths in the sample size and linear in their depth at a time logarithmic in both. Our analysis and convergence bounds are derived via the construction of a surrogate network with fixed activation patterns that can be transformed at any time to an equivalent ReLU network of a reasonable size.
  arXiv  Detail & Related papers  (2021-01-12T00:40:45Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)

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.