Conceptual diagram of the workflow for developing a species classifier
model - made with illustrations from Lucidchart.com and Amazon Web
Services icons
Libraries and Tools
Table 1: Fancy table with the different
libraries
I. DATA PHASE
Data Collection
Table 2: Table with where to get
data
Data Preparation
Data Organization - Training, Validation and Test
set
II. DEEP LEARNING PHASE
model creation
Figure 2: show confusion matrix - look at cancer paper by
thrun published in
nature
Table 3: show table of
results
model tuning
model saving
model inference -
development
III. DEPLOYMENT PHASE
model inference -
production
model inference -
deployment
Figure 3: show final
product
Conclusion
Although there have been many papers prototyping interesting
apllications of artificial intelligence, very few outline beginner
friendly - non domain approaches to classify species. This paper
illustrated the tools, steps and resources required to achieve this feat
with little domain knowledge of the subject. Like, the advent of
electricity in 19XX(quote edison) - it is the application of the tools
that will move humanity forward. This paper gives ecologists working
from the most advanced labs in the world to the least resourced labs
power to prototype world class classifiers for their specific subjects.
Acknowledgements
(optional)
I would like to thank my advisor Dr. Melissa Pespeni and the QUEST
fellowship under grant from NSF bla bla
A brief statement acknowledging collaborators and research assistants
who do not meet the criteria for authorship described above, or
acknowledging funding sources, providing relevant permit numbers
(including institutional animal use permits), or giving recognition to
nature reserves or other organizations that made the work possible.
Authors’ contributions
All submissions with more than one author must include an Authors’
contributions statement. All persons listed as authors on a paper are
expected to meet ALL of the following criteria for authorship:
substantial contributions to conception and design, or acquisition of
data, or analysis and interpretation of data, or drafting the article or
revising it critically for important intellectual content; final
approval of the version to be published; agreement to be accountable for
the aspects of the work that they conducted and ensuring that questions
related to the accuracy or integrity of any part of their work are
appropriately investigated and resolved. Acquisition of funding,
provision of facilities, or supervising the research group of authors
without additional contribution are not usually sufficient
justifications for authorship. The statement should include an
explanation of the contribution of each author. We suggest the following
format for the Authors’ contributions statement:
AB and CD conceived the ideas and designed methodology; CD and EF
collected the data; EF and GH analysed the data; AB and CD led the
writing of the manuscript. All authors contributed critically to the
drafts and gave final approval for publication.
Data Availability
To enable readers to locate archived data from papers, we require that
authors list the database and the respective accession numbers or DOIs
for all data from the manuscript that has been made publicly available.
For example, “Data available from the Dryad Digital Repository
http://dx.doi.org/10.5061/dryad.41qh7 (Kiere & Drummond 2016).”
When a DOI is available for the data, the full data citation should also
be given in the reference list. See below. Please see our editorial
policies page for further information
References
In text citations should follow the author-date method whereby the
author’s last name and the year of publication for the source should
appear in the text, for example, (Jones, 1998). The complete reference
list should appear alphabetically by name at the end of the paper.
Please note that a DOI should be provided for all references where
available.
You will not be asked to reformat references during submission or peer
review however, a sample of the most common entries in our reference
lists appears below.
Text Citations:
One author: Gabriel (2000) and (Gabriel, 2000) Two authors: (Mathes &
Severa, 2004) and Mathes and Severa (2004) Three to five authors (first
occurrence): Waterman, Roman, and Rock (1993) and (Waterman, Roman, &
Rock 1993) Six or more authors: Smith et al. (1999) and (Smith et al.,
1999)
Personal communication citations are not included in the reference list.
Cite personal communications in text only. Give the initials as well as
the surname of the communicator, and provide as exact a date as
possible.
References should be cited as ‘in press’ only if the paper has been
accepted for publication. Work not yet submitted for publication or
under review should be cited as ‘unpublished data’, with the author’s
initials and surname given; such work should not be included in the
Reference section. Any paper cited as ‘in press’ or under review
elsewhere must be uploaded as part of the manuscript submission as a
file ‘not for review’ so that it can be seen by the editors and, if
necessary, made available to the referees.
In Reference List: