Deep Learning with Eigenvalue Decay Regularizer

نویسنده

  • Oswaldo Ludwig
چکیده

This paper extends our previous work on regularization of neural networks using Eigenvalue Decay by employing a soft approximation of the dominant eigenvalue in order to enable the calculation of its derivatives in relation to the synaptic weights, and therefore the application of back-propagation, which is a primary demand for deep learning. Moreover, we extend our previous theoretical analysis to deep neural networks and multiclass classification problems. Our method is implemented as an additional regularizer in Keras, a modular neural networks library written in Python, and evaluated in the benchmark data sets Reuters Newswire Topics Classification, IMDB database for binary sentiment classification, MNIST database of handwritten digits and CIFAR-10 data set for image classification.

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

Deep Learning: Generalization Requires Deep Compositional Feature Space Design

Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several image classification experiments. We show that the information loss due to conv...

متن کامل

Fast Learning with Noise in Deep Neural Nets

Dropout has been raised as an effective and simple trick [1] to combat overfitting in deep neural nets. The idea is to randomly mask out input and internal units during training. Despite its usefulness, there has been very little and scattered understanding on injecting noise to deep learning architectures’ internal units. In this paper, we study the effect of dropout on both input and hidden l...

متن کامل

A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

Although deep learning has produced dazzling successes for applications of image, speech, and video processing in the past few years, most trainings are with suboptimal hyper-parameters, requiring unnecessarily long training times. Setting the hyper-parameters remains a black art that requires years of experience to acquire. This report proposes several efficient ways to set the hyper-parameter...

متن کامل

Feature Incay for Representation Regularization

Softmax loss is widely used in deep neural networks for multi-class classification, where each class is represented by a weight vector, a sample is represented as a feature vector, and the feature vector has the largest projection on the weight vector of the correct category when the model correctly classifies a sample. To ensure generalization, weight decay that shrinks the weight norm is ofte...

متن کامل

MDL Regularizer: A New Regularizer based on the MDL Principle

This paper proposes a new regularization method based on the MDL (Minimum Description Length) principle. An adequate precision weight vector is trained by approximately truncating the maximum likelihood weight vector. The main advantage of the proposed regularizer over existing ones is that it automatically determines a regularization factor without assuming any specific prior distribution with...

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:
  • CoRR

دوره abs/1604.06985  شماره 

صفحات  -

تاریخ انتشار 2016