Dynamically-Scaled Deep Canonical Correlation Analysis

نویسندگان

چکیده

Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections them. Several variants CCA have been introduced in the literature, particular, based on deep neural networks learning highly nonlinear transformations views. As these models are parameterized conventionally, their learnable parameters remain independent inputs after training process, which limits capacity representations. We introduce novel dynamic scaling an input-dependent canonical correlation model. In our deep-CCA models, last layer scaled second network that conditioned model’s input, resulting parameterization dependent input samples. evaluate model multiple datasets and demonstrate learned representations more comparison to conventionally-parameterized CCA-based also obtain preferable retrieval results.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Deep Canonical Correlation Analysis

We introduce Deep Canonical Correlation Analysis (DCCA), a method to learn complex nonlinear transformations of two views of data such that the resulting representations are highly linearly correlated. Parameters of both transformations are jointly learned to maximize the (regularized) total correlation. It can be viewed as a nonlinear extension of the linear method canonical correlation analys...

متن کامل

Deep Generalized Canonical Correlation Analysis

We present Deep Generalized Canonical Correlation Analysis (DGCCA) – a method for learning nonlinear transformations of arbitrarily many views of data, such that the resulting transformations are maximally informative of each other. While methods for nonlinear two-view representation learning (Deep CCA, (Andrew et al., 2013)) and linear many-view representation learning (Generalized CCA (Horst,...

متن کامل

Deep Variational Canonical Correlation Analysis

We present deep variational canonical correlation analysis (VCCA), a deep multiview learning model that extends the latent variable model interpretation of linear CCA (Bach and Jordan, 2005) to nonlinear observation models parameterized by deep neural networks (DNNs). Computing the marginal data likelihood, as well as inference of the latent variables, are intractable under this model. We deriv...

متن کامل

Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis

We study the problem of acoustic feature learning in the setting where we have access to another (non-acoustic) modality for feature learning but not at test time. We use deep variational canonical correlation analysis (VCCA), a recently proposed deep generative method for multi-view representation learning. We also extend VCCA with improved latent variable priors and with adversarial learning....

متن کامل

Triphone State-Tying via Deep Canonical Correlation Analysis

Context-dependent phone models are used in modern speech recognition systems to account for co-articulation effects. Due to the vast number of possible context-dependent phones, statetying is typically used to reduce the number of target classes for acoustic modeling. We propose a novel approach for state-tying which is completely data dependent and requires no domain knowledge. Our method firs...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Lecture Notes in Computer Science

سال: 2023

ISSN: ['1611-3349', '0302-9743']

DOI: https://doi.org/10.1007/978-3-031-33380-4_18