This letter introduces an abstract learning problem called the ``set embedding'': The objective is to map sets into probability distributions so as to lose less information. We relate set union and intersection operations with corresponding interpolations of probability distributions. We also demonstrate a preliminary solution with experimental results on toy set embedding examples.

For decades, researchers in fields, such as the natural and social sciences, have been verifying causal relationships and investigating hypotheses that are now well-established or understood as truth. These causal mechanisms are properties of the natural world, and thus are invariant conditions regardless of the collection domain or environment. We show in this paper how prior knowledge in the form of a causal graph can be utilized to guide model selection, i.e., to identify from a set of trained networks the models that are the most robust and invariant to unseen domains. Our method incorporates prior knowledge (which can be incomplete) as a Structural Causal Model (SCM) and calculates a score based on the likelihood of the SCM given the target predictions of a candidate model and the provided input variables. We show on both publicly available and synthetic datasets that our method is able to identify more robust models in terms of generalizability to unseen out-of-distribution test examples and domains where covariates have shifted.

Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks. Preventing forgetting is achieved by introducing a generative network which can produce data from previously seen tasks so that it can be rehearsed along side learning the new task. This has been found to be effective in both supervised and reinforcement learning. Our current work aims to further prevent forgetting by encouraging the generator to accurately generate features important for task retention. More specifically, the generator is improved by introducing a second discriminator into the Generative Adversarial Network which learns to classify between real and fake items from the intermediate activation patterns that they produce when fed through a continual learning agent. Using Atari 2600 games, we experimentally find that improving the generator can considerably reduce catastrophic forgetting compared to the standard pseudo-rehearsal methods used in deep reinforcement learning. Furthermore, we propose normalising the Q-values taught to the long-term system as we observe this substantially reduces catastrophic forgetting by minimising the interference between tasks' reward functions.

A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs utilize a contrastive approach for representation learning in environments with compositional structure. We structure each state embedding as a set of object representations and their relations, modeled by a graph neural network. This allows objects to be discovered from raw pixel observations without direct supervision as part of the learning process. We evaluate C-SWMs on compositional environments involving multiple interacting objects that can be manipulated independently by an agent, simple Atari games, and a multi-object physics simulation. Our experiments demonstrate that C-SWMs can overcome limitations of models based on pixel reconstruction and outperform typical representatives of this model class in highly structured environments, while learning interpretable object-based representations.

Schools like those in the Pennsylvania Montour School District have mandated AI in the grades 5-8 curriculum, and they are expanded the initiative in other grades as well. Educators have embedded artificial intelligence in STEM courses, and other subjects like Music, Computer Science and Media Arts also include AI in their curricula. Additionally, the district requires their students to take a stand-alone AI Ethics course that teaches students design and values.

We've been working hard on Version 7.0 of the freeCodeCamp curriculum. Some of these improvements - including 4 new Python certifications - will go live in early 2019. Note: if you're already going through the current version of the curriculum, keep going. As you'll see, there's no reason to stop. Will take a person with very basic computer knowledge...

The automated nature of such attacks means that they can be launched at speeds far in excess of what humans are capable of, he said, suggesting that attacks could happen on a microsecond-by-microsecond level. "We're going to have to understand the implications of, not people-to-machine attacks, but machine-to-machine attacks," said Mr. Fanning. Some security teams are using AI defensively, but cybersecurity leaders across sectors worry that the same technology could propel sophisticated attacks that will be difficult to fend off. A congressional report published last year raised the possibility of AI-based attacks overwhelming grid defenses. Utilities need to invest in defenses and do so quickly, said Mark James, an adjunct professor of law at Vermont Law School and a co-author of a report on state power utilities' cybersecurity practices, published this month.

The newest librarian at the University of Oklahoma is a robot. It's a chatbot, which library officials plan to add to the library's website this summer to answer some of the most common questions students come in with, as well as to help them get started with their research. The system can tackle things like "where can I print?" or "what databases do you have about biology?" Anything it can't answer gets sent to a human librarian. The bot is just one example of how college libraries and technologists are experimenting with artificial intelligence to support students and professors in their research. Algorithms may soon help them prepare their literature reviews by quickly finding the most important papers in an area, and help match researchers with peers in other disciplines doing similar work to form new collaborations.

When a given task becomes enjoyable, people tend to work harder and perform better. Schools and teachers have been using this principle to heighten the interest of young students in early childhood care and pedagogy. Integrating games into traditional teaching methods have been significant in enhancing their understanding and preparing them better for the next grade. Companies across the world too have started seeing a lot of potential in the similar application of game-design elements in non-game contexts. This becomes extremely relevant in a time when millennials make for nearly half of the workforce.

As I had always been in love with technology, I have a habit of exploring new technologies. I like to read about what's happening in the tech world and how these new technologies can disrupt the current industries. In the recent past, as I was exploring and reading extensively on what impact can recent technologies have over our lives, I quickly noticed that there were a few terms that were thrown around almost all over the place: AI, Data Science, Machine Learning, Deep Learning. Although, technically wrong, let's refer to these technologies as AI (Artificial Intelligence) in general. I was kinda hooked and I started to casually read about them as these technologies naturally appeared to have the potential to disrupt any industry imaginable.