Neural Networks Should Be Wide Enough to Learn Disconnected Decision
Regions

Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions

28 February 2018

Quynh N. Nguyen

Mahesh Chandra Mukkamala

Matthias Hein

Papers citing "Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions"

11 / 11 papers shown

Title
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 96 33 0 29 Apr 2023
Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes Christian Haase Christoph Hertrich Georg Loho 34 22 0 24 Feb 2023
$Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete$ Training Fully Connected Neural Networks is $\exists\mathbb{R}$ -Complete Daniel Bertschinger Christoph Hertrich Paul Jungeblut Tillmann Miltzow Simon Weber OffRL 64 30 0 04 Apr 2022
Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size Christoph Hertrich M. Skutella 52 21 0 28 May 2020
Universal Approximation with Deep Narrow Networks Patrick Kidger Terry Lyons 40 328 0 21 May 2019
A Survey of the Recent Architectures of Deep Convolutional Neural Networks Asifullah Khan A. Sohail Umme Zahoora Aqsa Saeed Qureshi OOD 65 2,271 0 17 Jan 2019
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity Chulhee Yun S. Sra Ali Jadbabaie 28 117 0 17 Oct 2018
Empirical Bounds on Linear Regions of Deep Rectifier Networks Thiago Serra Srikumar Ramalingam 8 42 0 08 Oct 2018
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 296 3,113 0 04 Nov 2016
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 326 5,847 0 08 Jul 2016
Benefits of depth in neural networks Matus Telgarsky 155 603 0 14 Feb 2016