Convolutional Neural Network (CNN) Training Algorithm

A Convolutional Neural Network (CNN) Training Algorithm is a deep NNet training algorithm that can be applied by a CNN training system (to solve a CNN training task which requires a CNN model).

• Context:
  • It can (typically) be a Feed-Forward Neural Network Training Algorithm.
  • …
• Counter-Example(s):
  • a Recurrent Neural Network Training Algorithm.
• See:, Pooling Operation.

---

---

References

2015

• http://white.stanford.edu/teach/index.php/An_Introduction_to_Convolutional_Neural_Networks
  • QUOTE: … FFNNs weren't good at dealing with many sorts of problems in practice. … What was needed was an architecture that exploited the two dimensional spacial constraints imposed by its input modality whilst reducing the amount of parameters involved in training. Convolutional neural networks are the architecture. … All of the current convolutional networks share the common problem of being strictly feed-forward. … While the best greedy learning algorithm for convolutional architectures is currently unclear (most deep learning involves unsupervised error signals), inroads are being made and the future for convolutional networks remains bright. …

2009

• (Lee, Grosse et al., 2009) ⇒ Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng. (2009). “Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations.” In: Proceedings of the 26th Annual International Conference on Machine Learning (ICML 2009).

---