卷积张量字典学习

  • kxx_xiaoming
    了解作者
  • matlab
    开发工具
  • 2.2MB
    文件大小
  • zip
    文件格式
  • 0
    收藏次数
  • 10 积分
    下载积分
  • 0
    下载次数
  • 2022-07-06 20:08
    上传日期
卷积张量字典学习算法的matlab代码,很详细
ConvDicLearnTensorFactor-master.zip
  • ConvDicLearnTensorFactor-master
  • code
  • fn-2d
  • cir_inv_2d.m
    172B
  • katri_rao4mat.m
    167B
  • ALS_2d.m
    2.4KB
  • kronecker_prod4mat.m
    269B
  • katri_rao.m
    67B
  • kronecker_prod4vec.m
    68B
  • mutip_matrix_katri_rao.m
    304B
  • circulant_projection_2d.m
    783B
  • normc.m
    321B
  • cir_square_dot_inv_2d.m
    1.7KB
  • circulant_2d.m
    265B
  • EigenVector4Circulant.m
    211B
  • cconv2.m
    338B
  • cconv2_runtime_vs_n.m
    269B
  • diag_blk_inv.m
    1.2KB
  • cconv2_reverse_revised.m
    680B
  • modeA_2d.m
    342B
  • cconv2_reverse.m
    373B
  • blkinv2.m
    192B
  • test.m
    1.6KB
  • my_orthogonalization_2d.m
    370B
  • matrix_katri_rao.m
    169B
  • ALS_2d_noDeflation.m
    2.3KB
  • Construct_Tensor_from_Data.m
    581B
  • normc_2d.m
    426B
  • T_fc_odot_fb_2d.m
    642B
  • fn
  • multip_circulant_col_coeff.m
    464B
  • modeA.m
    1KB
  • circulant.m
    5KB
  • cir_inv.m
    164B
  • katri_rao.m
    67B
  • circulant_projection.m
    737B
  • cir_square_dot_inv.m
    1.6KB
  • mutip_matrix_katri_rao.m
    304B
  • normc.m
    321B
  • ALS.m
    1.9KB
  • T_fc_odot_fb.m
    534B
  • matrix_katri_rao.m
    169B
  • Construct_Tensor_from_Data.m
    580B
  • circulant_row2col.m
    89B
  • main_decode_1d.m
    614B
  • main_learn_2d.m
    677B
  • main_decode_2d.m
    632B
  • main_learn_1d.m
    521B
  • main_learn_2d_notDeflation.m
    689B
  • data
  • syntheticData_L1.mat
    175.2KB
  • syntheticData_2d_L1.mat
    2MB
  • LICENSE
    11.1KB
  • README.md
    996B
内容介绍
# ConvDicLearnTensorFactor Tensor methods have emerged as a powerful paradigm for consistent learning of many latent variable models such as topic models, independent component analysis and dictionary learning. Model parameters are estimated via CP decomposition of the observed higher order input moments. However, in many domains, additional invariances such as shift invariances exist, enforced via models such as convolutional dictionary learning. In this paper, we develop novel tensor decomposition algorithms for parameter estimation of convolutional models. Our algorithm is based on the popular alternating least squares method, but with efficient projections onto the space of stacked circulant matrices. Our method is embarrassingly parallel and consists of simple operations such as fast Fourier transforms and matrix multiplications. Our algorithm converges to the dictionary much faster and more accurately compared to the alternating minimization over filters and activation maps.
评论
    相关推荐
    • image-sentiment-analysis.zip
      图片情感分析模型,基于卷积神经网络,以颜色特征为依据进行情感分类,图片情感极性分为积极和消极两类。
    • MATLABhanshu.rar
      matlab的函数目录,,作为初学者的函数字典,,很有参考价值
    • cnn.zip
      利用python中TensorFlow模块实现的基于cnn的文本分类算法
    • 迁移学习.rar
      学习迁移是指一种学习对另一种学习的影响,或习得的经验对完成其他活动的影响。迁移广泛存在于各种知识、技能与社会规范的学习中。
    • matlab函数目录
      matlab的函数目录,,作为初学者的函数字典,,很有参考价值
    • 自动识别交通牌(用不同尺度的CNN实现交通指示牌的识别)
      (不是完整项目,适用于学习)该项目是对Pierre Sermanet 和 Yannn LeCun的论文《Traffic Sign Recognition with Multi-Scale Convolutional Networks》的代码复现。 涉及技术:Pycharm + Keras + Python 3.6 + ...
    • NER-LSTM-CRF-master.zip
      一个易于使用的命名实体识别(NER)工具包,在张量流中实现了LSTM + [CNN] + CRF模型。 该项目短期内不再维护,PyTorch版本: : 1.型号 Bi-LSTM / Bi-GRU + [CNN] + CRF,其中CNN层针对英文,捕获字符特征,通过...
    • libiconv-1.1.tar.gz
      字符集转换程序
    • VisualC++.rar
      vc++数字图像处理 ,是一本很不错的介绍数字图像方面的书籍,这里有本书的全部源码
    • sharewareluncher.zip
      执行和去除共享软件日期限制的程序