X-Account-Key: account2
X-UIDL: 0000e1dd4877d5f6
X-Mozilla-Status: 0011
X-Mozilla-Status2: 00000000
X-Mozilla-Keys:                                                                                 
Return-Path: <juergen@idsia.ch>
Received: from ti-edu.ch (posta.ti-edu.ch [195.176.176.171])
	by mail-cc.srv.lexi.net (8.14.4/8.14.4) with ESMTP id t06McVSU123281
	for <Bill@billhowell.ca>; Tue, 6 Jan 2015 15:38:35 -0700
Received: from [92.104.56.54] (account juergen@idsia.ch HELO [192.168.1.106])
  by ti-edu.ch (CommuniGate Pro SMTP 6.0.9)
  with ESMTPSA id 102481682; Tue, 06 Jan 2015 23:38:29 +0100
Content-Type: text/plain; charset=windows-1252
Mime-Version: 1.0 (Mac OS X Mail 6.6 \(1510\))
Subject: Re: Interview for INNS BigData
From: Juergen Schmidhuber <juergen@idsia.ch>
In-Reply-To: <54AC61DD.90202@uniroma1.it>
Date: Tue, 6 Jan 2015 23:38:28 +0100
Cc: Asim Roy <ASIM.ROY@asu.edu>,
        "'Angelov, Plamen'" <p.angelov@lancaster.ac.uk>,
        "www.BillHowell.ca" <Bill@BillHowell.ca>,
        "Teng Teck Hou (Dr)" <THTeng@ntu.edu.sg>,
        "jiglesia@inf.uc3m.es" <jiglesia@inf.uc3m.es>
Message-Id: <446CA11B-A440-4F0C-878A-D8099BE21C78@idsia.ch>
References: <54AC61DD.90202@uniroma1.it>
To: Simone Scardapane <simone.scardapane@uniroma1.it>
X-Mailer: Apple Mail (2.1510)
X-Greylist: Sender IP whitelisted by DNSRBL, not delayed by milter-greylist-4.4.1 (mail-cc.srv.lexi.net [198.161.90.1]); Tue, 06 Jan 2015 15:38:35 -0700 (MST)
Content-Transfer-Encoding: 8bit
X-MIME-Autoconverted: from quoted-printable to 8bit by mail-cc.srv.lexi.net id t06McVSU123281

Dear Simone,

sure, we can do this. 

To facilitate this, here a 2012 interview - maybe one can cut and paste a few things from there:
http://www.kurzweilai.net/how-bio-inspired-deep-learning-keeps-winning-competitions

Of course some of this needs updates, especially the question:
"How do your team’s techniques differ from Google, Microsoft, and Nuance approaches to automated speech and image recognition?"
Because today all big companies (Google, Microsoft, Baidu) use our recurrent NNs for speech and images and other stuff!

Kindest regards,
Juergen


On Jan 6, 2015, at 11:29 PM, Simone Scardapane <simone.scardapane@uniroma1.it> wrote:

> Dear Prof. Schmidhuber,
> 
> I am Simone Scardapane, publicity co-chair for the upcoming INNS Big Data conference. I am writing to you because we are envisaging some interviews over the next months, to increase the interest in the main themes of our conference.  In particular, I am writing to know if you would like to participate in one, on the themes of deep and recurrent neural networks. Currently, we do not have additional details, since we wanted to check your possible availability first. I am copying the general chairs and the publicity committee to the email.
> 
> Thanking you in advance, I send my best regards,
> 
> Simone Scardapane
> --
> PhD Student - La Sapienza University of Rome
> Contact: visit my website
> -----
> Publicity Co-Chair for INNS Conference on Big Data 2015
> Follow us on: Twitter - Facebook - Google+



