Blind Bounded Source Separation Using Neural Networks with Local Learning Rules

• URL: http://arxiv.org/abs/2004.05479v1
• Date: Sat, 11 Apr 2020 20:20:22 GMT
• Title: Blind Bounded Source Separation Using Neural Networks with Local Learning Rules
• Authors: Alper T. Erdogan, Cengiz Pehlevan
• Abstract summary: We propose a new optimization problem, Bounded Similarity Matching (BSM) A principled derivation of an adaptive BSM algorithm leads to a recurrent neural network with a clipping nonlinearity. The network adapts by local learning rules, satisfying an important constraint for both biological plausibility and implementability in neuromorphic hardware.
• Score: 23.554584457413483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An important problem encountered by both natural and engineered signal processing systems is blind source separation. In many instances of the problem, the sources are bounded by their nature and known to be so, even though the particular bound may not be known. To separate such bounded sources from their mixtures, we propose a new optimization problem, Bounded Similarity Matching (BSM). A principled derivation of an adaptive BSM algorithm leads to a recurrent neural network with a clipping nonlinearity. The network adapts by local learning rules, satisfying an important constraint for both biological plausibility and implementability in neuromorphic hardware.

Related papers

• Point Source Identification Using Singularity Enriched Neural Networks [4.228167013618626]
  We develop a novel algorithm to identify point sources, utilizing a neural network combined with a singularity enrichment technique. We demonstrate the effectiveness of the method with several challenging experiments.
  arXiv  Detail & Related papers  (2024-08-17T08:51:18Z)
• Sound Source Separation Using Latent Variational Block-Wise Disentanglement [33.94867897638613]
  We present a hybrid classical digital signal processing/deep neural network (DSP/DNN) approach to source separation (SS) We show that the design choices and the variational formulation of the task at hand motivated by the classical signal processing theoretical results lead to robustness to unseen out-of-distribution data and reduction of the overfitting risk.
  arXiv  Detail & Related papers  (2024-02-08T07:22:39Z)
• Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation [17.740376367999705]
  We propose a biologically plausible neural network that extracts correlated latent sources by exploiting information about their domains. Online formulation of this optimization problem naturally leads to neural networks with local learning rules. Choices of simplex or polytopic source domains result in networks with piecewise-linear activation functions.
  arXiv  Detail & Related papers  (2022-10-09T11:03:16Z)
• Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources [19.938405188113027]
  We propose novel biologically-plausible neural networks for the blind separation of potentially dependent/correlated sources. We derive two-layer biologically-plausible neural network algorithms that can separate mixtures into sources coming from a variety of source domains. We demonstrate that our algorithms outperform other biologically-plausible BSS algorithms on correlated source separation problems.
  arXiv  Detail & Related papers  (2022-09-27T09:12:10Z)
• Physics informed neural networks for continuum micromechanics [68.8204255655161]
  Recently, physics informed neural networks have successfully been applied to a broad variety of problems in applied mathematics and engineering. Due to the global approximation, physics informed neural networks have difficulties in displaying localized effects and strong non-linear solutions by optimization. It is shown, that the domain decomposition approach is able to accurately resolve nonlinear stress, displacement and energy fields in heterogeneous microstructures obtained from real-world $mu$CT-scans.
  arXiv  Detail & Related papers  (2021-10-14T14:05:19Z)
• 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)
• A Neural Network with Local Learning Rules for Minor Subspace Analysis [12.437226707039446]
  We introduce a novel similarity matching objective for extracting the minor subspace, Minor Subspace Similarity Matching (MSSM) We derive an adaptive MSSM algorithm that naturally maps onto a novel neural network with local learning rules and gives numerical results showing that our method converges at a competitive rate.
  arXiv  Detail & Related papers  (2021-02-10T15:44:27Z)
• Provably Training Neural Network Classifiers under Fairness Constraints [70.64045590577318]
  We show that overparametrized neural networks could meet the constraints. Key ingredient of building a fair neural network classifier is establishing no-regret analysis for neural networks.
  arXiv  Detail & Related papers  (2020-12-30T18:46:50Z)
• 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)
• Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications [119.81868223344173]
  The paper investigates the general problem of resource allocation for mitigating channel fading effects in Free Space Optical (FSO) communications. Under this framework, we propose two algorithms that solve FSO resource allocation problems.
  arXiv  Detail & Related papers  (2020-07-27T17:38:51Z)
• Resource Allocation via Graph Neural Networks in Free Space Optical Fronthaul Networks [119.81868223344173]
  This paper investigates the optimal resource allocation in free space optical (FSO) fronthaul networks. We consider the graph neural network (GNN) for the policy parameterization to exploit the FSO network structure. The primal-dual learning algorithm is developed to train the GNN in a model-free manner, where the knowledge of system models is not required.
  arXiv  Detail & Related papers  (2020-06-26T14:20:48Z)

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.