Supplementary Material: Online Incremental Feature Learning with Denoising Autoencoders

نویسندگان

  • Guanyu Zhou
  • Kihyuk Sohn
  • Honglak Lee
چکیده

Roughly speaking, this update rule is based on the following idea: increase the number of feature increments when the performance improves (i.e., the model is not at optimum), and decrease the number of feature increments when there is minimal or no performance improvement (i.e., the model has converged). From this intuition, we consider the following update rule (referred to as “update rule I”):

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Online Incremental Feature Learning with Denoising Autoencoders

While determining model complexity is an important problem in machine learning, many feature learning algorithms rely on cross-validation to choose an optimal number of features, which is usually challenging for online learning from a massive stream of data. In this paper, we propose an incremental feature learning algorithm to determine the optimal model complexity for large-scale, online data...

متن کامل

Feature Transfer Learning for Speech Emotion Recognition

Speech Emotion Recognition (SER) has achieved some substantial progress in the past few decades since the dawn of emotion and speech research. In many aspects, various research efforts have been made in an attempt to achieve human-like emotion recognition performance in real-life settings. However, with the availability of speech data obtained from different devices and varied acquisition condi...

متن کامل

Marginalized Stacked Denoising Autoencoders

Stacked Denoising Autoencoders (SDAs) [4] have been used successfully in many learning scenarios and application domains. In short, denoising autoencoders (DAs) train one-layer neural networks to reconstruct input data from partial random corruption. The denoisers are then stacked into deep learning architectures where the weights are fine-tuned with back-propagation. Alternatively, the outputs...

متن کامل

Scheduled denoising autoencoders

We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is only slightly corrupted, the network tends to learn fine-grained features. Th...

متن کامل

Learning Representations of Affect from Speech

There has been a lot of prior work on representation learning for speech recognition applications, but not much emphasis has been given to an investigation of effective representations of affect from speech, where the paralinguistic elements of speech are separated out from the verbal content. In this paper, we explore denoising autoencoders for learning paralinguistic attributes, i.e. categori...

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

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012