Neural Network Projection Layer

A Neural Network Projection Layer is a neural network layer that ..

• Context:
  • It can be a Linear Projection Layer.
• Example(s):
  • …
• Counter-Example(s):
  • NNet Hidden Layer.
  • NNet Output Layer.
  • NNet Input Layer.
• See: Artificial Neural Network.

---

---

References

2013

• (Mikolov et al., 2013a) ⇒ Tomáš Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. (2013). “Efficient Estimation of Word Representations in Vector Space.” In: Proceedings of International Conference of Learning Representations Workshop.
  • QUOTE: … architecture for estimating neural network language model (NNLM) was proposed in [1], where a feedforward neural network with a linear projection layer and a non-linear hidden layer was used to learn jointly the word vector representation and a statistical language model. …

2001

• Feraund, R., Olivier J. Bernier, J-E. Viallet, and Michel Collobert. (2001). “A Fast and Accurate Face Detector based on Neural Networks.” In: Pattern Analysis and Machine Intelligence, IEEE Transactions on 23, no. 1.
  • QUOTE: … It depends of a fixed number weights, corresponding to the architecture of the neural network. … However, as we want to obtain a nonlinear dimension reduction and a nonlinear relation between the submanifold (the compression layer) and the projection layer (the output layer ...

---