# Projection Matrix A projection layer is just a simple matrix multiplication, or in the context of NN, a regular/dense/linear layer, without the non-linear activation in the end (sigmoid/tanh/relu/etc.) The idea is to **project** the (e.g.) 100K-dimensions discrete vector into a 600-dimensions continuous vector (I chose the numbers here randomly, "your mileage may vary"). The exact matrix parameters are learned through the training process. > t is simply projecting a higher dimensional vector onto a lower dimensional space --- Date: 20220901 Links to: Tags: #review References: * [machine learning - What is a projection layer in the context of neural networks? - Stack Overflow](https://stackoverflow.com/questions/37889914/what-is-a-projection-layer-in-the-context-of-neural-networks)