Category Archives: Machine Learning

Empfehlenswert: @mluebbecke “Digitalisierung und Vernetzung allein erzeugen noch keine Intelligenz” #Industrie40 #IoT #Mathematik #Digitalisierung

Taken from: https://mluebbecke.wordpress.com/2015/12/16/industrie-5-0/

@mluebbecke über . Hier nur zwei Highlights:

  1. “Bevor Sie “blind” Daten sammeln und “alles” vernetzen (oder vernetzbar machen), holen Sie sich Rat über die mathematischen Möglichkeiten, was mit welchen Daten erreichbar ist.”
  2. “Kaufen Sie keine Software, auf der nicht das Label “Mathematik inside” steht. Geben Sie sich nicht mit weniger als mathematischer Optimierung zufrieden. Ihre Mitbewerber werden es auch nicht tun.”

Den gesamten Beitrag finden Sie unter: https://mluebbecke.wordpress.com/2015/12/16/industrie-5-0/

CfP: Automated Design of #machinelearning and Search Algorithms

Industry is faced with solving complex optimization problems on a day to day basis in different domains including transportation, data mining, computer vision, computer security, robotics and scheduling amongst others. #machinelearning and search algorithms play an important role in solving such problems.
More: http://titancs.ukzn.ac.za/CIMADA2017.aspx

TechCrunch: We need a new open source model for AI and ML #openscience

It is not enough for the pioneers of AI and ML to share their code. The industry and the world needs a new open source model where AI and ML trained engines themselves are open sourced along with the data, features and real world performance details…” Read more: https://techcrunch.com/2017/01/28/ais-open-source-model-is-closed-inadequate-and-outdated/

Interesting paper: Deceiving Deep Neural Networks


The authors (Mahmood Sharif, Sruti Bhagavatula, Lujo Bauer and Michael K. Reiter) of the paper “Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition” [1] describe a new class of attacks that target face recognition systems: attacks that are 1. physically realizable and 2. at the same time are inconspicuous.
The authors investigate two categories of attacks:  1.  dodging attacks (the attacker seeks to have her face misidentified as any other arbitrary face) and  2. impersonation attacks (the adversary seeks to have a face recognized as a specific other face). Their approach is based on the observation that Deep Neural Networks can be misled by mildly perturbing inputs [2]. More: https://www.cs.cmu.edu/~sbhagava/

References

[1] M. Sharif, S. Bhagavatula, L. Bauer, and M. K. Reiter. Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition. In 23rd ACM Conference on Computer and Communications Security (CCS 2016), 2016.

[2] C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. J. Goodfellow, and R. Fergus. Intriguing properties of neural networks. In Proc. ICLR, 2014.