Working on gradient descent / backpropagation for a relational autoencoder. I’m not really sure this is needed yet, so I have to build the testing framework for it all. Separately I’m implementing a RL agent that uses Least Squares Policy Iteration to learn.

Let X and Y be two sets of training examples of sizes N and M respectively

Select and randomly

- Feed forward
- Step 1 – Train X
- Hold w and x constant and minimize cost by treating y’ as a parameter
- Calculate error on x side of cost function
- Backprop error
- Update W (and b) only on the X side

- Step 2 – Train Y
- Hold w and y constant and minimize cost by treating x’ as a parameter
- Calculate error on y side of cost function
- Backprop error
- Update W (and b) only on the Y side

### Like this:

Like Loading...

*Related*