{"version":"https://jsonfeed.org/version/1","title":"Journal — Akera, by Benjamin Akera","home_page_url":"https://benjaminakera.com","feed_url":"https://benjaminakera.com/journal/feed.json","description":"A place for my thoughts and notes as on life, philosophy, art, Artificial Intelligence and everything","items":[{"id":"https://benjaminakera.com/journal/init/","author":{"name":"Benjamin Akera","url":"https://benjaminakera.com"},"title":"[journal] Init","url":"https://benjaminakera.com/journal/init/","date_published":"2020-09-28T21:00:00.000-06:00","content_html":"
Initialization of a sample post to test the possibilities\n
Assumed audience: No one really, just curious\n
Yesterday I wrote at some length about how severely travel impacts my ability to keep up my normal routines. As I hoped, reflecting and planning a bit at the end of that post was a helpful bit of motivation today. I got up this morning and did a new variant on my push-up routine,[^push-ups] and then make a point to get out for a run early this afternoon. It helped. It helped a lot!
\nA brief Introduction to tackling climate change with Machine Learning\n
Assumed audience: all\n
I recently had the honor of delivering a keynote at the Deep Learning Indaba X conference in Cameroon. My talk focused on how machine learning can help mitigate climate change. Below you'll find the slides that accompanied my presentation.
\nThrough data visualizations, I aimed to tell a compelling story about the immense challenges posed by climate change. I also highlighted some promising applications of AI, both for mitigation and adaptation to climate change.
\nThis talk built off the amazing tutorials and insights from the Climate Change AI organization and their summer school. Special thanks to Dr. David Rolnick and Dr. Priya Donti from whom key points in this presentation are derived.
\nBird Distribution Modelling using Remote Sensing and Citizen Science data.\n
Assumed audience: researchers\n
Climate change is a major driver of biodiversity loss, changing the geographic range and abundance of many species. However, there remain significant knowledge gaps about the distribution of species, due principally to the amount of effort and expertise required for traditional field monitoring. We propose an approach leveraging computer vision to improve species distribution modelling, combining the wide availability of remote sensing data with sparse on-ground citizen science data. We introduce a novel task and dataset for mapping US bird species to their habitats by predicting species encounter rates from satellite images, along with baseline models which demonstrate the power of our approach. Our methods open up possibilities for scalably modelling ecosystems properties worldwide.
\nRead the paper here.
\n