Introduction

Deep learning, a branch of machine learning, is an artificial intelligence approach which has been used for pattern recognition across multiple domains \cite{Shen_2017,Golden_2017,Min_2016,Heaton_2016,Esteva2019,Esteva2017}.  Whereas other machine learning approaches have been used for acoustic classification \cite{Aide_2013}, ecological modelling and studying animal behaviour \cite{Olden_2008,Valletta_2017,Christin_2019}, deep learning approaches have demonstrated the ability to overcome several machine learning limitations. One of the challenges of machine learning approaches is the need for superior domain knowledge and high-level programming skills \cite{LeCun_2015,Christin_2019}\cite{inproceedings,NIPS2014_5347}. Further, the data feature engineering step in machine learning is a complex and often tedious task that discourages many from using these techniques. Deep learning overcomes this feature engineering step by ensuring that the algorithm finds features by itself automatically \cite{inbook}.
In ecology, however, the use of deep learning is still in its infancy. A literature  review puts both peers and non-peer reviewed papers at 46 as of April 2018, mostly using Convolutional Neural Networks (CNNs) and Recurrent Neural Networks(RNNs) \cite{Christin_2019}. This is despite its potential to revolutionalize applied ecology in identification and classification of species, behavioural studies, population monitoring and citizen science, ecosystem management and conservation \cite{Christin_2019,Lamba_2019,Miao_2019,Ditria_2019}. Several research articles continue to implement new, novel and interesting applications: such as using contextual data with image data and generating optimum evolution of camouflage using Generative Adversarial Networks \cite{Terry_2020,Talas_2019}. However, the techniques used still remain cryptic and inaccessible to most ecologists who are experts in their domains but who have no experience with these techniques. 
Naturalists have been identifying species for the past two centuries, laying the foundations of the ecological science. However, even today, most of the taxonomic work and species identification work is still manual and reliant on a few domain experts. Ecology in particular is ripe for the applications of deep learning owing to the increase in complex ecological datasets over the past few years ranging from genomic to ecosystem-scale data, also known as Big Data \cite{Hampton_2013,Farley_2018}. The Big data derived from the increasingly sophisticated automatic monitoring by sensors can no longer be manually processed as it is redundant and time consuming \cite{Weinstein_2017,Norouzzadeh_2018}. Deep learning is specifically better than other methods in dealing with non-linear complex data commonly encountered in ecology \cite{Christin_2019}. In fact, all winning methods for the most recent LifeCLEF contests which is a series of multimedia species identification challenges have been deep learning-based \cite{Joly_2017}. Reviews and proposals for these have been put forward and the field feels right for disruption \cite{Christin_2019,Lamba_2019}. Deep learning has been touted as a contender in solving problems with immediate application ranging from illegal trafficking of wildlife products to large scale automated ecosystem management tools - areas that are expensive and logistically expensive to manage \cite{Cantrell_2017,Christin_2019}
A lot of the challenges that prevented deep learning from having practical applications have been eliminated with advancements in research on transfer learning and data augmentation \cite{Shorten_2019}. This has led to a reduction in the data required to make accurate world-class models. Furthermore, the recent wave in computer hardware innovation for GPU’s and CPU’s has also accelerated by reducing the cost of accessing the processing power required for accurate model development. 
This paper is intended for non-AI experts who want to build species classifiers. We have attached an annotated  open source Jupyter Notebook. The tutorial is designed in a way that it can be implemented in the lowest resourced environment and unlock great application in taxa image identification in ecology the world over that we can hardly imagine at the moment. The code can be accessed from the Jupyter Notebook here: https://bit.ly/39woeLt