𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Discrepancy and approximations for bounded VC-dimension

✍ Scribed by Jiří Matoušek; Emo Welzl; Lorenz Wernisch

Publisher
Springer-Verlag
Year
1993
Tongue
English
Weight
683 KB
Volume
13
Category
Article
ISSN
0209-9683

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Polynomial Bounds for VC Dimension of Si
Polynomial Bounds for VC Dimension of Sigmoidal and General Pfaffian Neural Networks
✍ Marek Karpinski; Angus Macintyre 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 438 KB

We introduce a new method for proving explicit upper bounds on the VC dimension of general functional basis networks and prove as an application, for the first time, that the VC dimension of analog neural networks with the sigmoidal activation function \_( y)=1Â1+e & y is bounded by a quadratic poly

Sinusoidal and monotonic transfer functi
Sinusoidal and monotonic transfer functions: Implications for VC dimension
✍ R.J. Gaynier; T. Downs 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 282 KB

It is sometimes stated that neural networks that employ units with nonmonotonic transfer functions are more difficult to train than networks that use monotonic transfer functions, because the former can be expected to have more local minima. That this is often true arises from the fact that networks

An approximation scheme for strip packin
An approximation scheme for strip packing of rectangles with bounded dimensions
✍ W.Fernandez de La Vega; V. Zissimopoulos 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 597 KB

It is shown that for any positive E the strip-packing problem, i.e. the problem of packing a given list of rectangles into a strip of width 1 and minimum height. can be solled within I c 2: times the optimal height, in linear time, if the heights and widths of these rectangles are all bounded below