Dec 28, 2020
They solve the Schrödinger equation with the help of Artificial Intelligence
This is a review of some artificial intelligence news that happened throughout the week
Quantum chemistry aims to predict the chemical and physical properties of molecules based on the arrangement of their atoms in space, without time-consuming and resource-intensive laboratory experiments. This can be achieved by solving the Schrödinger equation, but in practice this is too difficult. A team of scientists from Freie Universität Berlin has developed a deep learning algorithm that can achieve a combination of precision and computational efficiency. The professor leading the research believes the approach may have a significant impact on the future of quantum chemistry.
Mapping craters on the moon with AI
Researchers in China, Italy and Iceland have used a machine learning artificial intelligence application to count and annotate the location of more than 100,000 craters on the moon. They described programming their system to recognize craters by training it with data collected by Chinese lunar orbiters, identifying and mapping craters on the moon is a slow and usually done process by hand, with researchers studying photographs and transferring those observations to maps or lunar globes. . In this new effort they have found a way to dramatically speed up the process by teaching a computer to identify craters and then count them.
Satellite detection of elephants
Using the highest resolution satellite imagery currently available from Maxar Technologies and deep learning, researchers from the University of Oxford Wildlife Conservation Research Unit and the Machine Learning Research Group have detected elephants from space with an accuracy comparable to human detection capabilities. The African elephant population has plummeted over the past century due to poaching, retaliatory killing for crop theft and habitat fragmentation. Keeping them requires knowing where they are and how many there are, which is why accurate monitoring is vitally important.
MuZero by DeepMind learns rules autonomously
DeepMind (a subsidiary of Alphabet) has made groundbreaking advancements using reinforcement learning to teach programs to master the board game Go and the strategy game Shogi, as well as chess and challenging Atari video games. In all those cases, the computers were given the rules of the game. A new report says that DeepMind’s MuZero has accomplished the same feats, and in some cases, surpassed previous programs without learning the rules first. The DeepMind programmers relied on a principle called lookahead. With that approach, MuZero evaluates a series of potential moves based on how an opponent would respond. While there are likely to be a staggering number of potential moves in complex games like chess, MuZero prioritizes the most relevant and likely moves, learning from successful tactics and avoiding the ones that failed.
Thanks for reading, I hope you have informed yourself of something new. See you in the next edition.
