Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources

• URL: http://arxiv.org/abs/2209.12894v1
• Date: Tue, 27 Sep 2022 09:12:10 GMT
• Title: Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources
• Authors: Bariscan Bozkurt, Cengiz Pehlevan, Alper T. Erdogan
• Abstract summary: 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.
• Score: 19.938405188113027
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Extraction of latent sources of complex stimuli is critical for making sense of the world. While the brain solves this blind source separation (BSS) problem continuously, its algorithms remain unknown. Previous work on biologically-plausible BSS algorithms assumed that observed signals are linear mixtures of statistically independent or uncorrelated sources, limiting the domain of applicability of these algorithms. To overcome this limitation, we propose novel biologically-plausible neural networks for the blind separation of potentially dependent/correlated sources. Differing from previous work, we assume some general geometric, not statistical, conditions on the source vectors allowing separation of potentially dependent/correlated sources. Concretely, we assume that the source vectors are sufficiently scattered in their domains which can be described by certain polytopes. Then, we consider recovery of these sources by the Det-Max criterion, which maximizes the determinant of the output correlation matrix to enforce a similar spread for the source estimates. Starting from this normative principle, and using a weighted similarity matching approach that enables arbitrary linear transformations adaptable by local learning rules, 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.

Related papers

• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Multivariate Systemic Risk Measures and Computation by Deep Learning Algorithms [63.03966552670014]
  We discuss the key related theoretical aspects, with a particular focus on the fairness properties of primal optima and associated risk allocations. The algorithms we provide allow for learning primals, optima for the dual representation and corresponding fair risk allocations.
  arXiv  Detail & Related papers  (2023-02-02T22:16:49Z)
• An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects [10.248235276871256]
  We propose a new causal inference framework to learn causal effects from multiple, decentralized data sources. We introduce an adaptive transfer algorithm that learns the similarities among the data sources. The proposed method is empirically shown to outperform the baselines on decentralized data sources with dissimilar distributions.
  arXiv  Detail & Related papers  (2023-01-01T04:57:48Z)
• 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)
• Semi-Blind Source Separation with Learned Constraints [1.2891210250935146]
  Blind source separation (BSS) algorithms are unsupervised methods for hyperspectral data analysis. In this article, we investigate a semi-supervised source separation approach in which we combine a projected alternating least-square algorithm with a learning-based regularization scheme. We show that this allows for an innovative BSS algorithm, with improved accuracy, which provides physically interpretable solutions.
  arXiv  Detail & Related papers  (2022-09-27T17:58:23Z)
• Iterative Sound Source Localization for Unknown Number of Sources [57.006589498243336]
  We propose an iterative sound source localization approach called ISSL, which can iteratively extract each source's DOA without threshold until the termination criterion is met. Our ISSL achieves significant performance improvements in both DOA estimation and source number detection compared with the existing threshold-based algorithms.
  arXiv  Detail & Related papers  (2022-06-24T13:19:44Z)
• Federated Offline Reinforcement Learning [55.326673977320574]
  We propose a multi-site Markov decision process model that allows for both homogeneous and heterogeneous effects across sites. We design the first federated policy optimization algorithm for offline RL with sample complexity. We give a theoretical guarantee for the proposed algorithm, where the suboptimality for the learned policies is comparable to the rate as if data is not distributed.
  arXiv  Detail & Related papers  (2022-06-11T18:03:26Z)
• A Discriminative Technique for Multiple-Source Adaptation [55.5865665284915]
  We present a new discriminative technique for the multiple-source adaptation, MSA, problem. Our solution only requires conditional probabilities that can easily be accurately estimated from unlabeled data from the source domains. Our experiments with real-world applications further demonstrate that our new discriminative MSA algorithm outperforms the previous generative solution.
  arXiv  Detail & Related papers  (2020-08-25T14:06:15Z)
• 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)
• Blind Bounded Source Separation Using Neural Networks with Local Learning Rules [23.554584457413483]
  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.
  arXiv  Detail & Related papers  (2020-04-11T20:20:22Z)

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.