Dr. Philipp Petersen Profile

Dr. Philipp Petersen

at Univ of Oxford

SPIE Involvement:

Author

Publications (2)

This will count as one of your downloads.

You will have access to both the presentation and article (if available).

DOWNLOAD NOW

This content is available for download via your institution's subscription. To access this item, please sign in to your personal account.

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Proceedings Article | 9 September 2019 Paper

The structure of spaces of neural network functions

Philipp Petersen, Mones Raslan, Felix Voigtlaender

Proc. SPIE. 11138, Wavelets and Sparsity XVIII

KEYWORDS: Neural networks, Machine learning

Read Abstract +

We analyse spaces of deep neural networks with a fixed architecture. We demonstrate that, when interpreted as a set of functions, spaces of neural networks exhibit many unfavourable properties: They are highly non-convex and not closed with respect to L^p-norms, for 0 < p < ∞ and all commonly-used activation functions. They are not closed with respect to the L^∞-norm for almost all practically-used activation functions; here, the (parametric) ReLU is the only exception. Finally, we show that the function that maps a family of neural network weights to the associated functional representation of a network is not inverse stable for every practically-used activation function.

Proceedings Article | 24 August 2017 Presentation + Paper

Memory-optimal neural network approximation

Helmut Bölcskei, Philipp Grohs, Gitta Kutyniok, Philipp Petersen

Proc. SPIE. 10394, Wavelets and Sparsity XVII

KEYWORDS: Signal processing, Neural networks

Read Abstract +

We summarize the main results of a recent theory—developed by the authors—establishing fundamental lower bounds on the connectivity and memory requirements of deep neural networks as a function of the complexity of the function class to be approximated by the network. These bounds are shown to be achievable. Specifically, all function classes that are optimally approximated by a general class of representation systems—so-called affine systems—can be approximated by deep neural networks with minimal connectivity and memory requirements. Affine systems encompass a wealth of representation systems from applied harmonic analysis such as wavelets, shearlets, ridgelets, α-shearlets, and more generally α-molecules. This result elucidates a remarkable universality property of deep neural networks and shows that they achieve the optimum approximation properties of all affine systems combined. Finally, we present numerical experiments demonstrating that the standard stochastic gradient descent algorithm generates deep neural networks which provide close-to-optimal approximation rates at minimal connectivity. Moreover, stochastic gradient descent is found to actually learn approximations that are sparse in the representation system optimally sparsifying the function class the network is trained on.

My Library

You currently do not have any folders to save your paper to! Create a new folder below.

Folder Name

Folder Description

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks. You are receiving this notice because your organization may not have SPIE eBooks access.*

*Shibboleth/Open Athens users─please sign in to access your institution's subscriptions.

To obtain this item, you may purchase the complete book in print format on SPIE.org.

PERSONAL SIGN IN
Full access may be available with your subscription

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Institutional Access:

PURCHASE THIS CONTENT

INTERESTED IN A FREE CORPORATE TRIAL?

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members:

Non-members: ADD TO CART

Keywords/Phrases

Search In:

Publication Years