DELTA BAR DELTA (JACOBS) - MULTI LAYER NETWORK HEURISTIC ALGORITHM

 Delta-Bar-Delta (Jacobs)

Since the cost surface for multi-layer networks can be complex, choosing a learning rate can be difficult. What works in one location of the cost surface may not work well in another location. Delta-Bar-Delta is a heuristic algorithm for modifying the learning rate as training progresses:

• Each weight has its own learning rate.
• For each weight: the gradient at the current timestep is compared with the gradient at the previous step (actually, previous gradients are averaged)
• If the gradient is in the same direction the learning rate is increased
• If the gradient is in the opposite direction the learning rate is decreased
• Should be used with batch only.

Let

g_ij(t) = gradient of E wrt w_ij at time t

then define

Then the learning rate m_ij for weight w_ij at time t+1 is given by

where b, g , and k are chosen by the hand.

Downsides:

• Knowing how to choose the parameters b, g , and k is not easy.
• Doesn't work for

Share on Facebook Share on Twitter Share on Google Plus

Declaimer - MARTINS LIBRARY

The publications and/or documents on this website are provided for general information purposes only. Your use of any of these sample documents is subjected to your own decision NB: Join our Social Media Network on Google Plus | Facebook | Twitter | Linkedin