top of page
source: https://www.extremetech.com/extreme/297048-deepmind-co-founder-mustafa-suleyman-placed-on-leave
Predicting the past with Ithaca
Article's Summary:
Provided with these inputs, Ithaca restores the text, and identifies the time and place in which the text was written. However, many of the inscriptions historians are interested in analysing with Ithaca are damaged and often missing chunks of text. Chronological attribution : When dating a text, Ithaca produces a distribution of predicted dates across all decades from 800 BCE to 800 CE. : When dating a text, Ithaca produces a distribution of predicted dates across all decades from 800 BCE to 800 CE. Saliency maps: To convey the results to historians, Ithaca uses a technique commonly used in computer vision that identifies which input sequences contribute most to a prediction.
Article's Keywords: 'bce', 'predictions', 'ithacas', 'date', 'using', 'ancient', 'text', 'historians', 'inscriptions', 'ithaca', 'predicting', 'past'
Accelerating fusion science through learned plasma control
Article's Summary:
Successfully controlling the nuclear fusion plasma in a tokamak with deep reinforcement learningTo solve the global energy crisis, researchers have long sought a source of clean, limitless energy. In a paper published today in Nature, we describe how we can successfully control nuclear fusion plasma by building and running controllers on the Variable Configuration Tokamak (TCV) in Lausanne, Switzerland. This “plasma sculpting” shows the RL system has successfully controlled the superheated matter and - importantly - allows scientists to investigate how the plasma reacts under different conditions, improving our understanding of fusion reactors. (credit: DeepMind & SPC/EPFL)In the video above, we see the plasma at the top of TCV at the instant our system takes control. We then created a range of plasma shapes being studied by plasma physicists for their usefulness in generating energy.
Article's Keywords: 'control', 'tokamak', 'learning', 'science', 'plasma', 'tcv', 'vessel', 'controllers', 'system', 'fusion', 'successfully', 'accelerating', 'learned'
MuZero’s first step from research into the real world
Article's Summary:
In a preprint published on arXiv, we detail our collaboration with YouTube to explore the potential for MuZero to improve video compression. In VP9, bitrate is optimised most directly through the Quantisation Parameter (QP) in the rate control module. Given a target bitrate, QPs for video frames are decided sequentially to maximize overall video quality. This works especially well in large, combinatorial action spaces, making it an ideal candidate solution for the problem of rate control in video compression. Beyond video compression, this first step in applying MuZero beyond research environments serves as an example of how our RL agents can solve real-world problems.
Article's Keywords: 'research', 'muzeros', 'muzero', 'video', 'vp9', 'bitrate', 'world', 'qp', 'muzerorc', 'youtube', 'encoded', 'real', 'quality', 'compression', 'step'
bottom of page