skip to main content
Idioma:

Learning to Reconstruct Signals From Binary Measurements

Tachella, Julián ; Laurent, Jacques

Transactions on Machine Learning Research Journal, 2023-11 [Periódico revisado por pares]

Ithaca: Cornell University Library, arXiv.org

Texto completo disponível

Citações Citado por
  • Título:
    Learning to Reconstruct Signals From Binary Measurements
  • Autor: Tachella, Julián ; Laurent, Jacques
  • Assuntos: Binary data ; Computer Science ; Computer Science - Information Theory ; Computer Science - Learning ; Mathematics ; Mathematics - Information Theory ; Signal reconstruction ; Statistics - Machine Learning ; Unsupervised learning
  • É parte de: Transactions on Machine Learning Research Journal, 2023-11
  • Descrição: Recent advances in unsupervised learning have highlighted the possibility of learning to reconstruct signals from noisy and incomplete linear measurements alone. These methods play a key role in medical and scientific imaging and sensing, where ground truth data is often scarce or difficult to obtain. However, in practice, measurements are not only noisy and incomplete but also quantized. Here we explore the extreme case of learning from binary observations and provide necessary and sufficient conditions on the number of measurements required for identifying a set of signals from incomplete binary data. Our results are complementary to existing bounds on signal recovery from binary measurements. Furthermore, we introduce a novel self-supervised learning approach, which we name SSBM, that only requires binary data for training. We demonstrate in a series of experiments with real datasets that SSBM performs on par with supervised learning and outperforms sparse reconstruction methods with a fixed wavelet basis by a large margin.
  • Editor: Ithaca: Cornell University Library, arXiv.org
  • Idioma: Inglês
Links
Voltar para lista de resultados
Resultado  1 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.