Notice of Intent to Compete

National Science Foundation Notice of Intent to Seek Approval to Revise and Extend an Information Collection Nuclear Regulatory Commission

The National Science Foundation (NSF) is announcing plans to request clearance of this collection. In accordance with the requirement of section 3506(c)(2)(A) of the Paperwork Reduction Act of 1995 (Pub. L. 104–13), we are providing opportunity for public comment on this action. After obtaining and considering public comment, NSF will prepare the submission requesting that OMB approve clearance...

Compete to Compute

Local competition among neighboring neurons is common in biological neural networks (NNs). We apply the concept to gradient-based, backprop-trained artificial multilayer NNs. NNs with competing linear units tend to outperform those with non-competing nonlinear units, and avoid catastrophic forgetting when training sets change over time.

To compete or not compete? Ingredients for a successful competition

As the number of competitions in the AI/Robotics field grows larger the question of what is the value of participating becomes more relevant and harder to answer. We look at multiple competition we have participated to, make some observations on them, try to determine what ingredients are needed for a successful competition, and raise questions for the future.

Notice to Contributors

Notice to the Reader

In this paper, we review two of the most well-known citation indexes and establish their connections with the Choquet and Sugeno integrals. In particular, we show that the recently established -index is a particular case of the Sugeno integral, and that the number of citations corresponds to the Choquet integral. In both cases, they use the same fuzzy measure. The results presented here permit ...