## Files

*   **train.csv** - the training dataset consisting of 1,760 bird call recordings, each classified as belonging to a species of bird
*   **test.csv** - the test set consisting of 16,626 bird call recording, unclassified
*   **birdsong_metadata.csv** - supplemental information specifying classified species and other relevant classification data regarding each bird call recording


## Task
Develop and train a neural network on the given train dataset (train.csv) to classify bird calls as belonging to 1 of 88 distinct bird species listed in the metadata (birdsong_metadata.csv), and subsequently test its performance using the provided test dataset (test.csv). 

There are 61 genera of auditory spectral features that can be extracted from the recordings in the datasets, and each species of bird can count on 20 data points. For additional statistics regarding the datasets, please refer to [https://www.kaggle.com/fleanend/birds-songs-numeric-dataset](url) at which the datasets were compiled.

Your submission.csv file should be formatted as id,species for each test set case.

## Submissions
In the Code tab below the competition header above, select the "New Notebook" button. This should navigate you to a blank local API, called a Kaggle Kernel, in which you will be writing your code. After you have finished programming, select the "Save Version" button in the upper right corner. In the pop-up window, select the option "Save & Run All (Commit)" from the dropdown menu before confirming "Save". To submit your Kernel's generated .csv submission file, navigate back to Code tab on the competition platform, and select the "Your Work" tab. Select the first/most recent notebook, and select the "Data" tab at the top of the screen under the notebook name. On the right below "Output", select the "submission.csv" file and submit to the competition.

To submit your Kaggle Kernel/notebook to event supervisors at machine.learning@birdso.org, navigate to your notebook's editing page and select "Download Notebook" from the File dropdown at the top. Upload your notebook to an email addressed  to machine.learning@birdso.org with your team name and number for evaluation.