Corpus ID: 12996116

Representational Learning with Extreme Learning Machine for Big Data Liyanaarachchi

  title={Representational Learning with Extreme Learning Machine for Big Data Liyanaarachchi},
  author={L. C. Kasun and Hongming Zhou and G. Huang and C. Vong}
Restricted Boltzmann Machines (RBM) and auto encoders, learns to represent features in a dataset meaningfully and used as the basic building blocks to create deep networks. This paper introduces Extreme Learning Machine based Auto Encoder (ELM-AE), which learns feature representations using singular values and is used as the basic building block for Multi Layer Extreme Learning Machine (ML-ELM). ML-ELM performance is better than auto encoders based deep networks and Deep Belief Networks (DBN… CONTINUE READING
142 Citations

Figures and Tables from this paper.

Hierarchical Extreme Learning Machine for unsupervised representation learning
  • 40
Kernel-Based Multilayer Extreme Learning Machines for Representation Learning
  • 66
  • PDF
Densely Connected Deep Extreme Learning Machine Algorithm
A fast learning algorithm for multi-layer extreme learning machine
  • 16
Stacked Autoencoder Based Deep Random Vector Functional Link Neural Network for Classification
  • 5
  • Highly Influenced
  • PDF
Data Partition Learning With Multiple Extreme Learning Machines
  • 34
Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning
  • Y. Yang, Q. Wu
  • Computer Science, Medicine
  • IEEE Transactions on Cybernetics
  • 2016
  • 53
Region-Enhanced Multi-layer Extreme Learning Machine
  • 4
Conditional Random Mapping for Effective ELM Feature Representation
  • 5


Efficient Learning of Deep Boltzmann Machines
  • 302
  • Highly Influential
  • PDF
Reducing the Dimensionality of Data with Neural Networks
  • 11,506
  • Highly Influential
  • PDF
Extreme learning machine: Theory and applications
  • 7,570
  • PDF
Extreme Learning Machine for Regression and Multiclass Classification
  • 3,621
  • PDF
Gradient-based learning applied to document recognition
  • 25,463
  • Highly Influential
  • PDF
Universal approximation using incremental constructive feedforward networks with random hidden nodes
  • 1,978
  • PDF
Extensions of Lipschitz maps into a Hilbert space
  • 1,091
Siew,“Universal Approximation Using Incremental Constructive Feedforward Networks with Random Hidden Node,
  • IEEE Transactions on Neural Networks,
  • 2006