Smaller generalization error derived for a deep residual neural network compared with shallow networks

• Estimates of the generalization error are proved for a residual neural network with L random Fourier features layers (z) over bar (l+1) = (z) over bar (l) + Re Sigma(K)(k=1)(b) over bar (lk) e(i omega lk (z) over barl) + Re Sigma(K)(k=1)

Subject headings

NATURVETENSKAP  -- Matematik -- Beräkningsmatematik (hsv//swe)

NATURAL SCIENCES  -- Mathematics -- Computational Mathematics (hsv//eng)

Keyword

residual network

deep random feature networks

supervised learning

error estimates

layer-by-layer algorithm

Publication and Content Type

ref (subject category)

art (subject category)