Baby names generated by a neural network

Single-layer_feedforward_artificial_neural_networkAndrej Karpath, a Stanford computer science PhD candidate, designed a plausible baby name generator, while working on recurrent neural networks (a type of artificial neural network).

According to Wikipedia, “in machine learning and cognitive science, artificial neural networks (ANNs) are a family of models inspired by biological neural networks (the central nervous systems of animals, in particular the brain) which are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown.”

In this case, Karpath fed the neural network 8000 real baby names as input and generated plausible baby names not in the original data set.

Examples: Antley, Nerille, Chelon, Walmor, Evena, Jeryly, Stachon, Charisa

 

Book Review: The Name Therapist

indexIn Duana Taha’s book, The Name Therapist, this “half-Gaelic, half-Egyptian TV screenwriter-slash-baby-name blogger turned advice columnist (on LaineyGossip.com) and self-declared ‘name therapist’ ” explores why names matter. This book review gives additional insight into the name concepts covered in the book and the style in which the author approaches them.

Call for Papers: ANS Conference Special Panel on Onomastics Beyond Academia

computer-564136_960_720The ANS is inviting abstract submissions for a special panel on “Onomastics Beyond Academia” for the 2017 annual conference to be held in conjunction with the Linguistic Society of America. The purpose of the panel is to highlight professional applications of onomastics outside of the university setting.

All professional names enthusiasts are invited to submit an abstract for a 20-minute presentation. Abstracts proposals should answer one or more of the following questions:

  1. How did your training in onomastics help your professional life, outside of academia (e.g. finding a job or building your own business)?
  2. How do you work with onomastic data in your profession?
  3. What are some of the most interesting challenges which you (and your colleagues) face in using names data?
  4. What new markets are opening for names enthusiasts?
  5. What practical recommendations would you give to other names enthusiasts who are interested in working outside of academia?

To submit a proposal, simply send a 250-word abstract proposal and a 100-word professional biography to Laurel Sutton [laurel@catchwordbranding.com] by the 15th of July 2016. For organizational purposes, please be sure to include the phrase “ANS 2017: Panel” in the subject line of your email.

All proposals will be subjected to blind review. Official notification of proposal acceptances will be sent on or before September 30, 2015. All authors whose papers have been accepted must be current members of the ANS and need to register with both the ANS and the Linguistic Society of America. Please feel free to contact Laurel Sutton should you have any questions or concerns.

We look forward to receiving your submission!