Engineering: Incorporating MLP into Detector
Engineering: Incorporating MLP into Detector
Issues
- Mean squared error is not appropriate
- does not represent desired result
- Token Error Rate is not differentiable
- cannot use back propagation
- Solution - two stage process
- Start with back propagation on mean squared error
- Continue with gradient descent on TER
- Simulated annealing to avoid local extrema
Implementation
- Validation - reproduce results from NICO implementation
- Gradient descent - recursive step size
- Annealing - add random dither to weights and repeat
- Results - best point gives 11.7% TER