Flickr PARK or BIRD: Dataversity Public Discussion: Dataversity

Flickr PARK or BIRD

Flickr has figured out how to tell if an image is of a bird or not,
using a deep convolutional neural network
<http://code.flickr.net/2014/10/20/introducing-flickr-park-or-bird/>

Seems to work pretty well, and did not take a research team and five years.

Rest of post

Neat. If we could get accurate OCR for bitmapped images of sequence
alignments I'd be a happy camper.

Rest of post

We could try!

On 21 October 2014 11:31, Paul P. Gardner <<email obscured>>
wrote:
> Neat. If we could get accurate OCR for bitmapped images of sequence
> alignments I'd be a happy camper.
>
> ----------------------------
> Paul P. Gardner
> Rutherford Discovery Fellow
> University of Canterbury
> www.ucbioinformatics.org
> ----------------------------
>
> On Tue, Oct 21, 2014 at 10:12 AM, Dan Randow <<email obscured>> wrote:
>
>>
>> Flickr has figured out how to tell if an image is of a bird or not,
>> using a deep convolutional neural network
>> <http://code.flickr.net/2014/10/20/introducing-flickr-park-or-bird/>
>>
>> Seems to work pretty well, and did not take a research team and five years.
>>
>> Dan
>>
>> --
>> Dan Randow
>> Collaboration Wrangler
>> http://randow.co.nz
>> +64 27 431 4928
>>
>>
>> --
>>
>> View topic http://dataversity.org.nz/r/topic/2pS9ZTCxjVcbndUolJvneZ
>>
>> Leave group mailto:dataversity_public_discuss@dataversity.org.nz
>> ?Subject=unsubscribe
>>
>> Start groups http://OnlineGroups.net
>>
>> This email may be confidential and subject to legal privilege, it may
>> not reflect the views of the University of Canterbury, and it is not
>> guaranteed to be virus free. If you are not an intended recipient,
>> please notify the sender immediately and erase all copies of the message
>> and any attachments.
>>
>> Please refer to http://www.canterbury.ac.nz/emaildisclaimer for more
>> information.
>>
>
> --
>
> View topic http://dataversity.org.nz/r/topic/4r3iCkJTVGPUvWnd1EnhUz
>
> Leave group
mailto:dataversity_public_discuss@dataversity.org.nz?Subject=unsubscribe

Rest of post

That'd be swell. Here are a few refs to get you started:

Aerts S, Haeussler M, van Vooren S, Griffith OL, Hulpiau P, Jones SJ,
Montgomery SB, Bergman CM, Open Regulatory Annotation Consortium. Text-mining
assisted regulatory annotation
<http://genomebiology.com/content/9/2/R31> *Genome
Biol*. 2008;9(2):R31. PMID: 18271954
<http://www.ncbi.nlm.nih.gov/pubmed/18271954> PMC: PMC2374703
<http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2374703/>

Haeussler M, Gerner M, Bergman CM. Annotating genes and genomes with DNA
sequences extracted from biomedical articles
<http://bioinformatics.oxfordjournals.org/content/27/7/980.long>
*Bioinformatics*. 2011 Apr 1;27(7):980-6. PMID: 21325301
<http://www.ncbi.nlm.nih.gov/pubmed/21325301> PMC: PMC3065681
<http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3065681/>

Van Noorden R. Trouble at the text mine
<http://www.nature.com/news/trouble-at-the-text-mine-1.10184> *Nature*.
2012 Mar 7;483(7388):134-5.

Rest of post

----------------------------
Paul P. Gardner
Rutherford Discovery Fellow
University of Canterbury
www.ucbioinformatics.org
----------------------------

On Tue, Oct 21, 2014 at 11:47 AM, Edward Abraham <<email obscured>>
wrote:

> We could try!
>
> On 21 October 2014 11:31, Paul P. Gardner <<email obscured>>
> wrote:
> > Neat. If we could get accurate OCR for bitmapped images of sequence
> > alignments I'd be a happy camper.
> >
> > ----------------------------
> > Paul P. Gardner
> > Rutherford Discovery Fellow
> > University of Canterbury
> > www.ucbioinformatics.org
> > ----------------------------
> >
> > On Tue, Oct 21, 2014 at 10:12 AM, Dan Randow <<email obscured>> wrote:
> >
> >>
> >> Flickr has figured out how to tell if an image is of a bird or not,
> >> using a deep convolutional neural network
> >> <http://code.flickr.net/2014/10/20/introducing-flickr-park-or-bird/>
> >>
> >> Seems to work pretty well, and did not take a research team and five
> years.
> >>
> >> Dan
> >>
> >> --
> >> Dan Randow
> >> Collaboration Wrangler
> >> http://randow.co.nz
> >> +64 27 431 4928
> >>
> >>
> >> --
> >>
> >> View topic http://dataversity.org.nz/r/topic/2pS9ZTCxjVcbndUolJvneZ
> >>
> >> Leave group mailto:dataversity_public_discuss@dataversity.org.nz
> >> ?Subject=unsubscribe
> >>
> >> Start groups http://OnlineGroups.net
> >>
> >> This email may be confidential and subject to legal privilege, it may
> >> not reflect the views of the University of Canterbury, and it is not
> >> guaranteed to be virus free. If you are not an intended recipient,
> >> please notify the sender immediately and erase all copies of the message
> >> and any attachments.
> >>
> >> Please refer to http://www.canterbury.ac.nz/emaildisclaimer for more
> >> information.
> >>
> >
> > --
> >
> > View topic http://dataversity.org.nz/r/topic/4r3iCkJTVGPUvWnd1EnhUz
> >
> > Leave group mailto:dataversity_public_discuss@dataversity.org.nz
> ?Subject=unsubscribe
> >
> > Start groups http://OnlineGroups.net
>
>
>
> --
>
> Edward Abraham
> www.dragonfly.co.nz
> Dragonfly Science, PO Box 27535, Wellington 6141, New Zealand
> Level 5, 158 Victoria Street, Te Aro, Wellington
> M: +64 21 989 454
> T: +64 4 385 9285
>
> --
>
> View topic http://dataversity.org.nz/r/topic/7f8rPvZhLrlOLjP1sIoYxE
>
> Leave group mailto:dataversity_public_discuss@dataversity.org.nz
> ?Subject=unsubscribe
>
> Start groups http://OnlineGroups.net
>
> This email may be confidential and subject to legal privilege, it may
> not reflect the views of the University of Canterbury, and it is not
> guaranteed to be virus free. If you are not an intended recipient,
> please notify the sender immediately and erase all copies of the message
> and any attachments.
>
> Please refer to http://www.canterbury.ac.nz/emaildisclaimer for more
> information.
>

Thanks Dan,

Thats funny! I saw that xkcd cartoon when it came out. Its impressive that
Flickr rose to the challenge.

The high tech near-future is going to be able to do all sorts of amazing things
with the date-time stamped and geotagged photos we take today. Imagine what we
could have done with millions of such images had they been taken 100 years ago.

I can see the NatureWatch NZ of the future identifying uploaded photos and
sounds all by itself, with crowdsourcing only needed for validation.

Keep on sharing those geotagged images.

Cheers,

Jon
https://www.flickr.com/photos/mollivan_jon/

Rest of post

________________________________________

Jon Sullivan, Ph.D.

Senior Lecturer

Department of Ecology

P.O. Box 84

Lincoln University / Te Whare Wanaka O Aoraki

Lincoln 7647

New Zealand

office: Room 436a, Burns building, Lincoln University campus

Cnr Springs & Ellesmere Junction Roads

email: <email obscured><mailto:Jon.Sullivan@lincoln.ac.nz>

tel: (03) 423 0756 *note the new number*

for international calls, replace (03) with (643)

profile: http://www.lincoln.ac.nz/staff-profile?staffId=Jon.Sullivan

my blog: http://jonsullivan.canterburynature.org
my observations on NatureWatch NZ: http://naturewatch.org.nz/observations/jon
Ecology Department blog: http://EcoLincNZ.blogspot.com

campus Fulbright advisor: ask me about opportunities for US study and research

____________________________________________________

On 21/10/2014, at 10:12 am, Dan Randow
<<email obscured><mailto:dan@randow.co.nz>> wrote:

Flickr has figured out how to tell if an image is of a bird or not,
using a deep convolutional neural network
<http://code.flickr.net/2014/10/20/introducing-flickr-park-or-bird/>

Seems to work pretty well, and did not take a research team and five years.

Dan

--
Dan Randow
Collaboration Wrangler
http://randow.co.nz
+64 27 431 4928

--

View topic http://dataversity.org.nz/r/topic/2pS9ZTCxjVcbndUolJvneZ

Leave group
mailto:dataversity_public_discuss@dataversity.org.nz?Subject=unsubscribe

Start groups http://OnlineGroups.net

________________________________
P Please consider the environment before you print this email.
"The contents of this e-mail (including any attachments) may be confidential
and/or subject to copyright. Any unauthorised use, distribution, or copying of
the contents is expressly prohibited. If you have received this e-mail in
error, please advise the sender by return e-mail or telephone and then delete
this e-mail together with all attachments from your system."

You cannot post because you are not logged in.

Flickr PARK or BIRD

Already a member?

Not a member?