Machine learning algorithms have successfully identified plant species in massive herbaria just by looking at the dried specimens. According to researchers, similar AI approaches could also be used identify the likes of fly larvae and plant fossils. From Nature: <\/p>\n
There are roughly 3,000 herbaria in the world, hosting an estimated 350 million specimens only a fraction of which has been digitized. But the swelling data sets, along with advances in computing techniques, enticed computer scientist Erick Mata-Montero of the Costa Rica Institute of Technology in Cartago and botanist Pierre Bonnet of the French Agricultural Research Centre for International Development in Montpellier, to see what they could make of the data. <\/p>\n
Researchers trained... algorithms on more than 260,000 scans of herbarium sheets, encompassing more than 1,000 species. The computer program eventually identified species with nearly 80% accuracy: the correct answer was within the algorithms top 5 picks 90% of the time. That, says (Penn State paleobotanist Peter) Wilf, probably out-performs a human taxonomist by quite a bit. <\/p>\n
Such results often worry botanists, Bonnet says, many of whom already feel that their field is undervalued. People feel this kind of technology could be something that will decrease the value of botanical expertise, he says. But this approach is only possible because it is based on the human expertise. It will never remove the human expertise. People would also still need to verify the results, he adds. <\/p>\n
\"Going deeper in the automated identification of Herbarium specimens\" (BMC Evolutionary Biology) <\/p>\n
In this TEDx Talk, science writer and umbraphile (an eclipse chaser) David Baron emphasizes the importance of witnessing a total solar eclipse firsthand (eye?) at least once in your lifetime. <\/p>\n
Below youll find an unhurried interview with Dr. Adam Gazzaley, who runs one of the West Coasts largest neuroscience labs at UCSF. There, his team carefully crafts video games with the potential to cure a wide range of neurological ailments. A direct heir to Adams research is now up for final FDA approval as a [] <\/p>\n
On August 20 and September 5, 1977, NASA launched two spacecraft, Voyager 1 and 2, on a grand tour of the solar system and into the mysteries of interstellar space. It was an incredibly audacious mission, and its still going. My friend Timothy Ferris produced the Voyager golden record thats attached to each of the [] <\/p>\n
This project management bundle will help you get organized and learn how to lead a team to success. You can pay what you want for these five courses when you pick them up from the Boing Boing Store.To help you become an invaluable asset for your company, this bundle includes a curated collection of professional [] <\/p>\n
Despite the push towards USB-C as the one connector to rule them all, most peripherals in the wild are still largely USB-A. Since theres little reason to upgrade all of your old flash drives, wired keyboards, and game controllers, youll need a decent hub to keep them all talking to your new computer.The MondoHub Master [] <\/p>\n
You dont always have to pay out the nose for household items, everyday accessories, or memorable gifts. If youre searching for something unexpected that can be had for less than two sawbucks, take a look at the following goods:20oz Insulated Water Bottle ($18.99)This stainless steel water bottle is double-walled with vacuum-sealed insulation to keep drinks [] <\/p>\n
<\/p>\n
Read the original: <\/p>\n
Artificial intelligence identifies plant species by looking at them - Boing Boing<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Machine learning algorithms have successfully identified plant species in massive herbaria just by looking at the dried specimens. According to researchers, similar AI approaches could also be used identify the likes of fly larvae and plant fossils Continue reading