Goto

Collaborating Authors

 matterhorn


Causal Explanations of Structural Causal Models

Zečević, Matej, Dhami, Devendra Singh, Rothkopf, Constantin A., Kersting, Kristian

arXiv.org Artificial Intelligence

In explanatory interactive learning (XIL) the user queries the learner, then the learner explains its answer to the user and finally the loop repeats. XIL is attractive for two reasons, (1) the learner becomes better and (2) the user's trust increases. For both reasons to hold, the learner's explanations must be useful to the user and the user must be allowed to ask useful questions. Ideally, both questions and explanations should be grounded in a causal model since they avoid spurious fallacies. Ultimately, we seem to seek a causal variant of XIL. The question part on the user's end we believe to be solved since the user's mental model can provide the causal model. But how would the learner provide causal explanations? In this work we show that existing explanation methods are not guaranteed to be causal even when provided with a Structural Causal Model (SCM). Specifically, we use the popular, proclaimed causal explanation method CXPlain to illustrate how the generated explanations leave open the question of truly causal explanations. Thus as a step towards causal XIL, we propose a solution to the lack of causal explanations. We solve this problem by deriving from first principles an explanation method that makes full use of a given SCM, which we refer to as SC$\textbf{E}$ ($\textbf{E}$ standing for explanation). Since SCEs make use of structural information, any causal graph learner can now provide human-readable explanations. We conduct several experiments including a user study with 22 participants to investigate the virtue of SCE as causal explanations of SCMs.


Matterhorn sways to a seismic beat, interstellar propulsion system remains science fiction, goldfish drives a car – Physics World

#artificialintelligence

The Matterhorn, an Alpine peak that straddles the border between Switzerland and Italy, is one of the most iconic mountains in the world. Isolated at the head of the Zermatt Valley, climbing the perfectly shaped mountain, which has a summit height of 4470 m above sea level, is on the to-do list of thousands of climbers – and some physicists. In 2019, an international team of scientists set out to take a closer look at the Matterhorn and installed several seismometers at different locations to record its movement. They found that despite the Matterhorn appearing like a huge immovable mass, it is in fact constantly on the move, swaying gently back and forth about once every two seconds. The researchers say that this subtle vibration, with a fundamental frequency of 0.42 Hz, is stimulated by seismic energy in the Earth originating from oceans and earthquakes, as well as – rather surprisingly – human activity.


Arm v9 promises ray tracing for smartphones and a big performance boost

PCWorld

Arm said Tuesday that ray tracing and variable rate shading will migrate from the PC to Arm-powered smartphones and tablets as part of Armv9, the next-generation CPU architecture that the company expects will power the next decade of Arm devices. Chips based upon the v9 architecture will be released in 2021, providing an estimated 30-percent improvement in performance over the next two Arm chip generations and the devices that run them. Arm's v9 will also add SVE2, new AI-specific instructions that will probably be used for the AI image processing used on smartphones, such as portrait mode. Arm v9 will also include what Arm is calling Realms, a hardware container of sorts specifically designed to protect virtual machines and secure applications. As an intellectual-property licensing company, Arm enjoys a unique position in the computing industry.


Disney unveils 'paintcopter' graffiti drone armed with a spray can

Daily Mail - Science & tech

A graffiti-spraying drone known as a'paintcopter' can can draw complex designs on walls and 3D objects and could help decorators colour hard-to-reach spots and eliminate the need for ladders and scaffolding. Developed by Disney, the autonomous drone is equipped with a spray-paint gun and uses cameras to work out where to draw. Experiments so far show the drone's ability to produce simple line drawings such as a bear and a mountain as well as colouring in whole sections of a wall. The product is still in development but could carry out low-skilled tasks such as filling in sections of a wall, leaving humans to do more intricate work. A graffiti-spraying drone known as a'paintcopter' can can draw complex designs on walls and 3D objects and could eliminate the need for ladders and scaffolding Disney's'paintcopter' is attached to a power cable and a supply of paint. It means the graffiti drone can work for long periods to carry out complex decorating tasks.