On the Principles of Deep Feedforward ReLU Networks

• URL: http://arxiv.org/abs/2607.07035v1
• Date: Wed, 08 Jul 2026 06:09:54 GMT
• Title: On the Principles of Deep Feedforward ReLU Networks
• Abstract summary: This paper systematically studies the mechanism of deep feedforward ReLU networks with multiple hidden layers.<n>It successfully explains the training solution obtained by the back-propagation algorithm.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The architecture of deep feedforward neural networks is ubiquitous in deep learning, either as a whole system or as a subnetwork of other architectures, and thus its mechanism is a key ingredient of the black box of neural networks. On the basis of the simplest two-layer ReLU network, this paper systematically studies the mechanism of deep feedforward ReLU networks with multiple hidden layers and successfully explains the training solution obtained by the back-propagation algorithm. The concept of a path, especially in terms of the relationships between paths, plays a central role in uncovering the mystery of the black box. It is shown that a unit of a deep ReLU network can form a piecewise linear manifold to divide the input space, instead of a hyperplane of the two-layer case. How to efficiently use the hidden-layer units to produce both linear functions and partitions of the input space is also a central problem. The principles of a two-layer ReLU network can be generalized to the deeper case to a large extent, such as multiple strict partial orders and continuity restriction. The combination of the basic and simple principles proposed can yield complicated instantiations including the training solutions, and in this sense the black box of deep feedforward ReLU networks is revealed.

Related papers

• On the Principles of ReLU Networks with One Hidden Layer [0.0]
  It remains unclear how to interpret the mechanism of its solutions obtained by the back-propagation algorithm.<n>It is shown that, both theoretically and experimentally, the training solution for the one-dimensional input could be completely understood.
  arXiv  Detail & Related papers  (2024-11-11T05:51:11Z)
• Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs [63.768739279562105]
  We show that for a particular choice of mask weights that do not depend on the learning targets, this kernel is equivalent to the NTK of the gated ReLU network on the training data. A consequence of this lack of dependence on the targets is that the NTK cannot perform better than the optimal MKL kernel on the training set.
  arXiv  Detail & Related papers  (2023-09-26T17:42:52Z)
• On the training and generalization of deep operator networks [11.159056906971983]
  We present a novel training method for deep operator networks (DeepONets) DeepONets are constructed by two sub-networks. We establish the width error estimate in terms of input data.
  arXiv  Detail & Related papers  (2023-09-02T21:10:45Z)
• Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks [44.31729147722701]
  We show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks.<n>This work makes progress towards understanding the provable benefit of three-layer neural networks over two-layer networks in the feature learning regime.
  arXiv  Detail & Related papers  (2023-05-11T17:19:30Z)
• Universal Solutions of Feedforward ReLU Networks for Interpolations [0.0]
  This paper provides a theoretical framework on the solution of feedforward ReLU networks for generalizations. To three-layer networks, we classify different kinds of solutions and model them in a normalized form; the solution finding is investigated by three dimensions, including data, networks and the training. To deep-layer networks, we present a general result called sparse-matrix principle, which could describe some basic behavior of deep layers.
  arXiv  Detail & Related papers  (2022-08-16T02:15:03Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks [75.33431791218302]
  We study the training problem of deep neural networks and introduce an analytic approach to unveil hidden convexity in the optimization landscape. We consider a deep parallel ReLU network architecture, which also includes standard deep networks and ResNets as its special cases.
  arXiv  Detail & Related papers  (2021-10-18T18:00:36Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Quasi-Equivalence of Width and Depth of Neural Networks [10.365556153676538]
  We investigate if the design of artificial neural networks should have a directional preference. Inspired by the De Morgan law, we establish a quasi-equivalence between the width and depth of ReLU networks. Based on our findings, a deep network has a wide equivalent, subject to an arbitrarily small error.
  arXiv  Detail & Related papers  (2020-02-06T21:17:32Z)
• A Rigorous Framework for the Mean Field Limit of Multilayer Neural Networks [9.89901717499058]
  We develop a mathematically rigorous framework for embedding neural networks in the mean field regime. As the network's widths increase, the network's learning trajectory is shown to be well captured by a limit. We prove several properties of large-width multilayer networks.
  arXiv  Detail & Related papers  (2020-01-30T16:43:34Z)

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.