1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.
10 years of news and resources for members of the IEEE Signal Processing Society
Neural networks with rectified linear unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the underlying data distribution being, e.g., Gaussian, or require the network size and/or training size to be sufficiently large. In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted. Leveraging the power of random noise perturbation, the paper entitled Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization by Gang Wang, Georgios Giannakis and Jie Chen published in IEEE Transactions on Signal Processing in May 2019 presents a novel stochastic gradient descent (SGD) algorithm, which can provably train any single-hidden-layer ReLU network to attain global optimality, despite the presence of infinitely many bad local minima, maxima, and saddle points in general. This result is the first of its kind, requiring no assumptions on the data distribution, raining/network size, or initialization. Convergence of the resultant iterative algorithm to a global minimum is analyzed by establishing both an upper bound and a lower bound on the number of non-zero updates to be performed. Moreover, generalization guarantees are developed for ReLU networks trained with the novel SGD leveraging classic compression bounds. These guarantees highlight a key difference (at least in the worst case) between reliably learning a ReLU network as well as a leaky ReLU network in terms of sample complexity. Numerical tests using both synthetic data and real images validate the effectiveness of the algorithm and the practical merits of the theory.
|Enhancements added to OU Analytics - Geographic Map||1 November 2019|
|Series to Highlight Women in Signal Processing: Sheila S. Hemami||1 November 2019|
|Redesigned OU Monthly Statistics Now Available||1 November 2019|
|OU Analytics - A Valuable Resource for Volunteers||1 November 2019|
|Inactive Chapters||1 November 2019|
|OU Analytics - Latest Enhancement||1 November 2019|
|Call for Nominations: Fellow Evaluation Committee - Extended to November 22||22 November 2019|
© Copyright 2019 IEEE – All rights reserved. Use of this website signifies your agreement to the IEEE Terms and Conditions.
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.