Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Introduction to Artificial Neural Networks – Part 1. Parent comment
- Use the tanh activation function.
- Use many hidden nodes, e.g. 100 or 1000 for complex tasks.
- Tune the learning rate.
- Add a penalty of k*w^2 to each hidden node. Tune the parameter k to minimize the held-out error.
- If this isn't working, plot the error on the training set as you train. It should decrease to 0.
Read Yann LeCun's efficient backprop work for more tips.
There are no comments on this comment yet.
- Use the tanh activation function.
- Use many hidden nodes, e.g. 100 or 1000 for complex tasks.
- Tune the learning rate.
- Add a penalty of k*w^2 to each hidden node. Tune the parameter k to minimize the held-out error.
- If this isn't working, plot the error on the training set as you train. It should decrease to 0.
Read Yann LeCun's efficient backprop work for more tips.