Collaborating Authors


World's smallest Rubik's Cube to be sold in Japan

The Japan Times

Japanese toy-maker MegaHouse Corp. said Wednesday it will launch the world's smallest working Rubik's Cube, weighing about 2 grams and measuring 0.99 centimeter on each side. On the same day, the Bandai Namco Holdings Inc. subsidiary started accepting orders for the product online. It is priced at ¥198,000 in Japan, including delivery costs. Delivery will start in late December. The Rubik's Cube, invented by Erno Rubik from Hungary in 1974, hit store shelves across the world in 1980. In Japan, MegaHouse has shipped out over 14 million cubes.

Towards Autonomous MR imaging using world models


MR imaging is a powerful and diverse imaging technique employed to investigate and diagnose a range of diseases in different body areas. MRI scans are acquired by employing specific parameters in a "sequence" to encode in data in arbitrary space known as "k-space". Image is reconstructed by applying mathematical transforms (mainly Fourier) to the k-space data. To obtain images of particular contrast (T1w, T2w, T2* etc) optimal sequence settings must be employed. Briefly, image contrast arise from magnetic property of the hydrogen atoms, that can varied setting such as echo time and Tr in sequence setting.

A connected Rubik's Cube will let speed cubers compete remotely


In-person competition is a no-go in many disciplines amid the COVID-19 pandemic, but speed cubers will be still able to battle opponents remotely in the Rubik's Cube World Cup. Rubik's has revealed the Connected Cube, which links to your phone or tablet and tracks your solve times and progress in real-time. It's more of a traditional cube than GoCube, which is largely a STEM-focused toy. Both use the same platform and can connect to the Rubik's Arena community, which has almost 47,000 players. As such, amateur and professional cubers can take part in this year's World Cup without having to travel, as long as they have a Connected Cube or GoCube. Qualifiers start August 15th and run through October 10th.

'The Speed Cubers' takes on the world of competitive Rubik's Cube solving


Speedcubing is the sport of solving a classic Rubik's Cube -- or a related combination puzzle -- in the shortest amount of time possible. And, no, it is not for the faint of heart. The new Netflix documentary on this subject, The Speed Cubers, dives headfirst into the friendly but competitive speedcubing culture. The 40-minute film is one of three new documentary shorts debuting on Netflix this summer. The Speed Cubers centers on a couple of professional competitors who go head-to-head at the World Cube Association World Championship in Melbourne, Australia, in 2019.

GPT-3 Creative Fiction


What if I told a story here, how would that story start?" Thus, the summarization prompt: "My second grader asked me what this passage means: …" When a given prompt isn't working and GPT-3 keeps pivoting into other modes of completion, that may mean that one hasn't constrained it enough by imitating a correct output, and one needs to go further; writing the first few words or sentence of the target output may be necessary.

Predictive Queries vs Supervised ML Models


Predictive queries resemble normal database queries with the exception that they provide predictions about the unknown, while the traditional database queries provide facts about the known. Here's an example of the BQL (Bayesian Query Language) query done against BayesLite database:

Python may get pattern matching syntax


The creators of the Python language are mulling a new proposal, PEP 622, that would finally bring a pattern matching statement syntax to Python. The new pattern matching statements would give Python programmers more expressive ways of handling structured data, without having to resort to workarounds. Pattern matching is a common feature of many programming languages, such as switch/case in C. It allows one of a number of possible actions to be taken based on the value of a given variable or expression. While Python has lacked a native syntax for pattern matching, it has been possible to emulate it with if/elif/else chains or a dictionary lookup. Supported pattern match types include literals, names, constant values, sequences, a mapping (basically, the presence of a key-value pair in the expression), a class, a mixture of the above, or any of those plus conditional expressions.

Plausible Reasoning about EL-Ontologies using Concept Interpolation Artificial Intelligence

Description logics (DLs) are standard knowledge representation languages for modelling ontologies, i.e. knowledge about concepts and the relations between them. Unfortunately, DL ontologies are difficult to learn from data and time-consuming to encode manually. As a result, ontologies for broad domains are almost inevitably incomplete. In recent years, several data-driven approaches have been proposed for automatically extending such ontologies. One family of methods rely on characterizations of concepts that are derived from text descriptions. While such characterizations do not capture ontological knowledge directly, they encode information about the similarity between different concepts, which can be exploited for filling in the gaps in existing ontologies. To this end, several inductive inference mechanisms have already been proposed, but these have been defined and used in a heuristic fashion. In this paper, we instead propose an inductive inference mechanism which is based on a clear model-theoretic semantics, and can thus be tightly integrated with standard deductive reasoning. We particularly focus on interpolation, a powerful commonsense reasoning mechanism which is closely related to cognitive models of category-based induction. Apart from the formalization of the underlying semantics, as our main technical contribution we provide computational complexity bounds for reasoning in EL with this interpolation mechanism.

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors Artificial Intelligence

The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse plan towards the goal and then gradually filling in details. In contrast, current learning approaches for visual prediction and planning fail on long-horizon tasks as they generate predictions (1) without considering goal information, and (2) at the finest temporal resolution, one step at a time. In this work we propose a framework for visual prediction and planning that is able to overcome both of these limitations. First, we formulate the problem of predicting towards a goal and propose the corresponding class of latent space goal-conditioned predictors (GCPs). GCPs significantly improve planning efficiency by constraining the search space to only those trajectories that reach the goal. Further, we show how GCPs can be naturally formulated as hierarchical models that, given two observations, predict an observation between them, and by recursively subdividing each part of the trajectory generate complete sequences. This divide-and-conquer strategy is effective at long-term prediction, and enables us to design an effective hierarchical planning algorithm that optimizes trajectories in a coarse-to-fine manner. We show that by using both goal-conditioning and hierarchical prediction, GCPs enable us to solve visual planning tasks with much longer horizon than previously possible.

Contextual and Possibilistic Reasoning for Coalition Formation Artificial Intelligence

In multiagent systems, agents often have to rely on other agents to reach their goals, for example when they lack a needed resource or do not have the capability to perform a required action. Agents therefore need to cooperate. Then, some of the questions raised are: Which agent(s) to cooperate with? What are the potential coalitions in which agents can achieve their goals? As the number of possibilities is potentially quite large, how to automate the process? And then, how to select the most appropriate coalition, taking into account the uncertainty in the agents' abilities to carry out certain tasks? In this article, we address the question of how to find and evaluate coalitions among agents in multiagent systems using MCS tools, while taking into consideration the uncertainty around the agents' actions. Our methodology is the following: We first compute the solution space for the formation of coalitions using a contextual reasoning approach. Second, we model agents as contexts in Multi-Context Systems (MCS), and dependence relations among agents seeking to achieve their goals, as bridge rules. Third, we systematically compute all potential coalitions using algorithms for MCS equilibria, and given a set of functional and non-functional requirements, we propose ways to select the best solutions. Finally, in order to handle the uncertainty in the agents' actions, we extend our approach with features of possibilistic reasoning. We illustrate our approach with an example from robotics.