Artwork

Content provided by Maxime Lenormand. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Maxime Lenormand or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

Ben Strong: We have Foundation Models of Earth, now What? Earth Index - MBM#69

1:05:35
 
Share
 

Manage episode 428397728 series 2913396
Content provided by Maxime Lenormand. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Maxime Lenormand or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.

Ben Strong is the Science & Machine Learning Lead at Earth Genome, an NGO working on the intersection of data, science & digital design. Most recently they've been working on Earth Index, an application built on top of Earth embeddings from foundation models. This conversation is the "so what" of Earth foundational model

Sponsor: OpenCage

Use OpenCage for your geocoding needs with their API
Geomob

About

Shownotes

Note: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.

Timestamps

(00:00) - Intro
(00:46) - Sponsor: OpenCage
(02:12) - Ben introduces himself
(03:28) - "DNA sequencing" for Earth
(13:37) - Not building another Foundation Model
(18:06) - Earth embeddings: So what?
(21:49) - What does locally finetuned mean?
(25:48) - Invite only for now: Why?
(29:31) - Journalistic applications
(31:59) - Yet another tool for finding images?
(35:09) - Deciding what to work on
(38:35) - Designing for simplicity
(44:14) - So, why hasn't Google made this?
(51:18) - Funding
(59:54) - Book & podcast Recommendations

  continue reading

82 episodes

Artwork
iconShare
 
Manage episode 428397728 series 2913396
Content provided by Maxime Lenormand. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Maxime Lenormand or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.

Ben Strong is the Science & Machine Learning Lead at Earth Genome, an NGO working on the intersection of data, science & digital design. Most recently they've been working on Earth Index, an application built on top of Earth embeddings from foundation models. This conversation is the "so what" of Earth foundational model

Sponsor: OpenCage

Use OpenCage for your geocoding needs with their API
Geomob

About

Shownotes

Note: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.

Timestamps

(00:00) - Intro
(00:46) - Sponsor: OpenCage
(02:12) - Ben introduces himself
(03:28) - "DNA sequencing" for Earth
(13:37) - Not building another Foundation Model
(18:06) - Earth embeddings: So what?
(21:49) - What does locally finetuned mean?
(25:48) - Invite only for now: Why?
(29:31) - Journalistic applications
(31:59) - Yet another tool for finding images?
(35:09) - Deciding what to work on
(38:35) - Designing for simplicity
(44:14) - So, why hasn't Google made this?
(51:18) - Funding
(59:54) - Book & podcast Recommendations

  continue reading

82 episodes

All episodes

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide

Listen to this show while you explore
Play