Incremental Learning of Convolutional Neural Networks

  title={Incremental Learning of Convolutional Neural Networks},
  author={Dusan Medera and Stefan Babinec},
Convolutional neural networks provide robust feature extraction with ability to learn complex, highdimensional non-linear mappings from collection of examples. To accommodate new, previously unseen data, without the need of retraining the whole network architecture we introduce an algorithm for incremental learning. This algorithm was inspired by AdaBoost algorithm. It utilizes ensemble of modified convolutional neural networks as classifiers by generating multiple hypotheses. Furthermore, with… Expand
5 Citations
Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
  • 41
  • Highly Influenced
  • PDF
AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks
  • PDF
Improving Facial Action Unit Recognition Using Convolutional Neural Networks
Forward Vehicle Detection Based on Incremental Learning and Fast R-CNN
  • Kaijing Shi, Hong Bao, Nan Ma
  • Computer Science
  • 2017 13th International Conference on Computational Intelligence and Security (CIS)
  • 2017
  • 14


Learn++: an incremental learning algorithm for supervised neural networks
  • 746
  • PDF
Neural Networks: Tricks of the Trade
  • 925
  • PDF
GradientBased Learning Applied to Document Recognition
  • 2,815
Training convolutional filters for robust face detection
  • M. Delakis, C. Garcia
  • Computer Science
  • 2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)
  • 2003
  • 9
  • PDF
A Short Introduction to Boosting
  • 2,779
  • PDF
Bootstrap - Inspired Techniques in Computation Intelligence
  • R. Polikar
  • Computer Science
  • IEEE Signal Processing Magazine
  • 2007
  • 134
  • PDF
A theory of the learnable
  • 1,787
  • PDF
Nonlinear neural networks: Principles, mechanisms, and architectures
  • 1,538
  • PDF
Classifier Conditional Posterior Probabilities
  • 88
  • PDF