Women in STEM

Women in Science Technology Engineering and Technology is a hot topic at the moment – even being covered in Animal Conservation and many blog posts. I just came across this graphic from engineeringdegree.net explaining attrition in the sciences – why women drop out of the science ladder as they progress. It would be great to see it extended to postgraduate and research jobs, as female attrition reaches it peak post-PhD, allegedly due to conflicts between academic careers and child-raising. For example, around 46 % of those being awarded undergraduate science degrees in the USA are women, but this percentage drops to 39 % for masters degrees, 33 % for doctoral degrees and – at the end of the career spectrum – 6 % for full professorships. Clearly, today’s challenge is not only to get women into science, but to keep them.

girls-in-science1

Posted in Uncategorized | Leave a comment

Science Uncovered

On Friday the 27th of September, the Natural History Museum London is holding a free evening where the public gets to mingle with scientists, and participate in debates and activities. I am running a debate on “Are all species equal?”, so feel free to pop in – the event runs from 16.00 pm to midnight.

science-uncovered-jellyfish-490_122370_2

 

Posted in Uncategorized | Leave a comment

End of summer & The Nature Conservancy article

The summer has been extremely busy: coming back from Australia, attending the BES Macroecology Symposium, the International Congress for Conservation Biology and INTECOL, where you might have caught one of my talks.

The only thing to show for it is this blurb on the Brisbane Student Conference, published at the Nature Conservancy. Read Eddie Game’s article here.

I will soon be getting back to work, pushing ideas around so expect more blog posts from now on!

I am also very excited about leading a debate on the 27th of September at the Natural History Museum’s Science Uncovered, on “Are all species equal?”. Please share your thoughts and arguments, it should be a very interesting night!

Posted in Uncategorized | Leave a comment

Talk at the University of Queensland

UQlogo

I am giving a seminar this Friday 3rd of May at the University of Queensland, 2pm in room 257 Goddard Building :)

 

Posted in Uncategorized | 1 Comment

Australian Museum Sydney

When I arrived in Sydney, I was all excited about exploring the city

When I arrived in Sydney, I was all excited about exploring the city

Instead, I was introduce to my new workplace, the basement of the Australian Museum Spirit House

Instead, I was introduced to my new workplace, the basement of the Australian Museum Spirit House

Maybe unfortunately, the Australian Museum has very extensive collections

Maybe unfortunately, the Australian Museum has very extensive collections

There were many, may crayfishes

There were many, may crayfishes

After five days of breathing ethanol and squinting at the digital callipers, I finally got out of the basement

After five days of breathing ethanol and squinting at the digital callipers, I finally got out of the basement

To rainy Sydney :(

To rainy Sydney

Actually, there was one sunny day

Actually, there was one sunny day

And I did go hiking, which made it all worth it!

And I did go hiking, which made it all worth it!

Now off the analyze my 1807 crayfish specimens across 563 species. I will see the sunlight again in a few months!

Posted in Uncategorized | 1 Comment

Machine Learning reading list

I have been asked by many, many people for some introductory reading on Machine Learning for ecologists. Here are my favourite references!

 

Textbooks

Elements of Statistical Learning (Hastie)

Elements of Statistical Learning (Hastie)

Hastie (2009) The Elements of Statistical Learning, Springer.

I believe is the best textbook around for Machine Learning. Quite math-heavy, but has good explanations of algorithm convergence and real-life examples on the use of ML. Online chapters may be available through your university.

 

 

 

Pattern Classification (Duda)

Pattern Classification (Duda)

Duda (2001) Pattern Classification.

Has a good chapter on estimating and comparing classifiers.

 

 

 

 

 

Statistical Pattern Recognition (Webb)

Statistical Pattern Recognition (Webb)

Webb (2002) Statistical Pattern Recognition.

Particularly good for performance measures and feature selection.

 

 

 

 

 

Pattern Recognition and Neural Networks (Ripley)

Pattern Recognition and Neural Networks (Ripley)

Ripley (1996) Pattern recognition and neural networks

I haven’t used it extensively, but have been recommended it from neural networks users.

 

 

 

 

Ecological Applications of ML

Recknagel F (2001) Applications of machine learning to ecological modelling. Ecological Modelling 146:303– 310.

Olden JD, Lawler JJ, Poff NL (2008) Machine learning methods without tears: a primer for ecologists. The Quarterly review of biology 83:171–93.

 

Tree-based methods

Cutler RD et al. (2007) Random forests for classification in ecology. Ecology 88:2783–92.

De’ath G (2007) Boosted Trees for Ecological Modeling and Prediction. Ecology 88:243–251.

Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. The Journal of Animal Ecology 77:802–13. An excellent guide to boosted regression trees with custom functions.

Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9:181–199.

 

Neural Networks

Lek S, Gue JF (1999) Artificial neural networks as a tool in ecological modelling, an introduction. Ecological Modelling 120:65 – 73.

Ozesmi S, Tan C, Ozesmi U (2006) Methodological issues in building, training, and testing artificial neural networks in ecological applications. Ecological Modelling 195:83–93.

Warner B, Misra M (1996) Understanding Neural Networks as Statistical Tools. The American Statistician 50:284–293.

 

Comparison of ML tools

Kampichler C, Wieland R, Calmé S, Weissenberger H, Arriaga-Weiss S (2010) Classification in conservation biology: A comparison of five machine-learning methods. Ecological Informatics 5:441–450.

Keller RP, Kocev D, Džeroski S (2011) Trait-based risk assessment for invasive species: high performance across diverse taxonomic groups, geographic ranges and machine learning/statistical tools. Diversity and Distributions 17:451–461.

 

Concepts in ML

I find it generally difficult to find information on the conceptual/philosophical basis of ML so let me know if you are aware of others!

Breiman L (2001) Statistical modeling: the two cultures. Statistical Science 16:199–231.

Make sure you download the version with replies from influential statisticians. Might radically change your views on algorithmic modelling, GLMs and statistical inference!

Glymour C, Madigan D, Pregibon D (1997) Statistical Themes and Lessons for Data Mining, in Data Mining and Knowledge Discovery (Kluwer Academic Publishers, Netherlands), pp 11–28.

Has some interesting points on inference from ML.

 

Package

I use caret in R, which automates a lot of the training and data pre-processing. The vignettes are very helpful. http://caret.r-forge.r-project.org/

Posted in Uncategorized | 1 Comment

Seminar at the Australian National University Canberra

ANUNext week I will be visiting the Macroecology and Macroevolution Group at the Australian National University in Canberra. I will also be giving a seminar entitled Cost-effective global biodiversity monitoring under uncertainty (quite a mouthful!) Wednesday April 10th at 12 noon in the Gould Building seminar room.

Posted in Uncategorized | 1 Comment