Capsule Network Performance on Complex Data

نویسندگان

  • Edgar Xi
  • Selina Bing
  • Yang Jin
چکیده

In recent years, convolutional neural networks (CNN) have played an important role in the field of deep learning. Variants of CNN’s have proven to be very successful in classification tasks across different domains. However, there are two big drawbacks to CNN’s: their failure to take into account of important spatial hierarchies between features, and their lack of rotational invariance [1]. As long as certain key features of an object are present in the test data, CNN’s classify the test data as the object, disregarding features’ relative spatial orientation to each other. This causes false positives. The lack of rotational invariance in CNN’s would cause the network to incorrectly assign the object another label, causing false negatives. To address this concern, Hinton et al. propose a novel type of neural network using the concept of capsules in a recent paper. With the use of dynamic routing and reconstruction regularization, the capsule network model would be both rotation invariant and spatially aware. [1]

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

Performance Appraisal of Research and Development Projects Value-Chain for Complex Products and Systems: The Fuzzy Three-Stage DEA Approach

The purpose of the current research is to provide a performance appraisal system capable of considering the value chain network structure of research and development (R&D) projects for Complex products and systems (CoPS) under uncertainty of data. Therefore, in order to achieve this goal, a network data envelopment analysis (NDEA) approach and the possibilistic programming to provide a new fuzz...

متن کامل

An Integrated Approach for Measuring Performance of Network structure: Case study on power plants

Data envelopment analysis (DEA) and balanced scorecard (BSC) are two well-known approaches for measuring performance of decision making units (DMUs). BSC is especially applied with quality measures, whereas, when the quantity measures are used to evaluate, DEA is more appropriate. In the real-world, DMUs usually have complex structures such as network structures. One of the well-known network s...

متن کامل

Link Prediction using Network Embedding based on Global Similarity

Background: The link prediction issue is one of the most widely used problems in complex network analysis. Link prediction requires knowing the background of previous link connections and combining them with available information. The link prediction local approaches with node structure objectives are fast in case of speed but are not accurate enough. On the other hand, the global link predicti...

متن کامل

Performance evaluation of chain saw machines for dimensional stones using feasibility of neural network models

Prediction of the production rate of the cutting dimensional stone process is crucial, especially when chain saw machines are used. The cutting dimensional rock process is generally a complex issue with numerous effective factors including variable and unreliable conditions of the rocks and cutting machines. The Group Method of Data Handling (GMDH) type of neural network and Radial Basis Functi...

متن کامل

Reliability and Performance Evaluation of Fault-aware Routing Methods for Network-on-Chip Architectures (RESEARCH NOTE)

Nowadays, faults and failures are increasing especially in complex systems such as Network-on-Chip (NoC) based Systems-on-a-Chip due to the increasing susceptibility and decreasing feature sizes. On the other hand, fault-tolerant routing algorithms have an evident effect on tolerating permanent faults and improving the reliability of a Network-on-Chip based system. This paper presents reliabili...

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/1712.03480  شماره 

صفحات  -

تاریخ انتشار 2017