Information Potential Auto-Encoders
نویسندگان
چکیده
In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized by minimization of the mutual information between input and encoding variables of AEs during the training phase. In order to estimate the entropy of the encoding variables and the mutual information, we propose a non-parametric method. We also give an information theoretic view of Variational AEs (VAEs), which suggests that VAEs can be considered as parametric methods that estimate entropy. Experimental results show that the proposed non-parametric models have more degree of freedom in terms of representation learning of features drawn from complex distributions such as Mixture of Gaussians, compared to methods which estimate entropy using parametric approaches, such as Variational AEs.
منابع مشابه
On the Latent Space of Wasserstein Auto-Encoders
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders. We highlight the potential of WAEs for representation learning with promising results on a benchmark disentanglement task.
متن کاملLearning Discrete Representations via Information Maximizing Self-Augmented Training
Our method is related to denoising auto-encoders (Vincent et al., 2008). Auto-encoders maximize a lower bound of mutual information (Cover & Thomas, 2012) between inputs and their hidden representations (Vincent et al., 2008), while the denoising mechanism regularizes the auto-encoders to be locally invariant. However, such a regularization does not necessarily impose the invariance on the hidd...
متن کاملRate-Distortion Auto-Encoders
A rekindled the interest in auto-encoder algorithms has been spurred by recent work on deep learning. Current efforts have been directed towards effective training of auto-encoder architectures with a large number of coding units. Here, we propose a learning algorithm for auto-encoders based on a rate-distortion objective that minimizes the mutual information between the inputs and the outputs ...
متن کاملTraining Auto-encoders Effectively via Eliminating Task-irrelevant Input Variables
Auto-encoders are often used as building blocks of deep network classifier to learn feature extractors, but task-irrelevant information in the input data may lead to bad extractors and result in poor generalization performance of the network. In this paper,via dropping the task-irrelevant input variables the performance of auto-encoders can be obviously improved .Specifically, an importance-bas...
متن کاملLatent Dimensionality and Random Encoders
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders.
متن کاملDeep Health Indicator Extraction: A Method based on Auto- encoders and Extreme Learning Machines
In this paper, we propose a novel deep learning method for feature extraction in prognostics and health management applications. The proposed method is based on Extreme Learning Machines (ELM) and Auto-Encoders (AE), which have demonstrated very good performance and very short training time compared to other deep learning methods on several applications, including image recognition problems. Th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1706.04635 شماره
صفحات -
تاریخ انتشار 2017