1. MLPfit: a tool to design and use Multi-Layer Perceptrons J. Schwindling, B. Mansoulié CEA / Saclay FRANCE Neural Networks, Multi-Layer Perceptrons: What are they ? Applications Approximation theory Unconstrained Minimization About training ... MLPfit Numerical Linear Algebra Statistics
2.
3.
4.
5.
6.
7.
8. Learning methods Stochastic minimization Linear model fixed steps [variable steps] Remarks: - derivatives known - other methods exist Global minimization Non-Linear weights All weights Linear model steepest descent with fixed steps or line search Quadratic model (Newton like) Conjugate gradients or BFGS with line search Solve LLS
9.
10.
11.
12.
13. Comparison on a toy problem fit the function x 2 sin(5xy) by a 2-10-1 MLP learning curves: (all curves = 2 minutes CPU)