We tackle two long-standing problems related to re-expansions in heuristic search algorithms. For graph search, A* can require $\Omega(2^{n})$ expansions, where $n$ is the number of states within the final $f$ bound. Existing algorithms that address this problem like B and B' improve this bound to $\Omega(n^2)$. For tree search, IDA* can also require $\Omega(n^2)$ expansions. We describe a new algorithmic framework that iteratively controls an expansion budget and solution cost limit, giving rise to new graph and tree search algorithms for which the number of expansions is $O(n \log C)$, where $C$ is the optimal solution cost. Our experiments show that the new algorithms are robust in scenarios where existing algorithms fail. In the case of tree search, our new algorithms have no overhead over IDA* in scenarios to which IDA* is well suited and can therefore be recommended as a general replacement for IDA*.

This paper introduces the concept of kernels on fuzzy sets as a similarity measure for $[0,1]$-valued functions, a.k.a. \emph{membership functions of fuzzy sets}. We defined the following classes of kernels: the cross product, the intersection, the non-singleton and the distance-based kernels on fuzzy sets. Applicability of those kernels are on machine learning and data science tasks where uncertainty in data has an ontic or epistemistic interpretation.

Empowerment is an information-theoretic method that can be used to intrinsically motivate learning agents. It attempts to maximize an agent's control over the environment by encouraging visiting states with a large number of reachable next states. Empowered learning has been shown to lead to complex behaviors, without requiring an explicit reward signal. In this paper, we investigate the use of empowerment in the presence of an extrinsic reward signal. We hypothesize that empowerment can guide reinforcement learning (RL) agents to find good early behavioral solutions by encouraging highly empowered states. We propose a unified Bellman optimality principle for empowered reward maximization. Our empowered reward maximization approach generalizes both Bellman's optimality principle as well as recent information-theoretical extensions to it. We prove uniqueness of the empowered values and show convergence to the optimal solution. We then apply this idea to develop off-policy actor-critic RL algorithms for high-dimensional continuous domains. We experimentally validate our methods in robotics domains (MuJoCo). Our methods demonstrate improved initial and competitive final performance compared to model-free state-of-the-art techniques.

W e present a Markov model at the discourse level for Steven Pinker's "mentalese", or chains of mental states that transcend the spoken/written forms. Such (potentially) universal temporal structures of textual pa tterns lead us to a language-independent semantic representation, or a translationally-invariant word embe dding, thereby forming the common ground for both comprehensibility within a given language and transla tability between different languages. Applying our model to documents of moderate lengths, without relying on external knowledge bases, we reconcile Noam Chomsky's "poverty of stimulus" paradox with statisti cal learning of natural languages. W e human beings distinguish ourselves from other animals ( 1-3), in that our brain development ( 4-6) enables us to convey sophisticated ideas and to share individual experience s, via languages ( 7-9). Texts written in natural languages constitute a major medium that perpetuates our civilizations ( 10), as a cumulative body of knowledge.

Last year saw the rise of the threat of deepfakes – a technique used to combine and superimpose images and videos onto others using a machine learning algorithm, creating hyper-realistic but fake content. AI buffs have split into two major groups – one working to make such images and video more realistic, and another developing tools that would tell users whether a video has been manipulated or not. A team of researchers from the University of California at Riverside and the R&D firm Mayachitra have developed a novel deep-learning architecture that can detect content-changing manipulation. This is not the first study on the problem, but this neural network appears to have gone further in recognising deepfakes than its predecessors. Different manipulation techniques may create a convincing video for human eyes, but the algorithm is able to see minor distortions, such as shearing and compression. It exploits resampling features, a long short-term memory (LSTM) based network, and encoder-decoder architectures in order to analyse videos pixel by pixel, and is said to be capable of spotting whole patches of the footage that have been doctored.

Michael Krigsman: Artificial intelligence in drug discovery is a relatively new field. Thank you so much for watching. Before we begin, please subscribe on YouTube and subscribe to our newsletter. You can do that right now. Alex Zhavoronkov, he is the CEO of Insilico. Tell us briefly about Insilico Medicine and tell us the things that you're working on. Alex Zhavoronkov: We are focused primarily on applying next-gen AI techniques to drug discovery, biomarker development, and also aging research. We focus specifically on two machine learning techniques. Those are the techniques we are most expert in our field. We use those techniques for two purposes. One is identifying biological targets and constructing biomarkers from multiple data types and also generating new molecules, new molecular structures with a specific set of properties. We were one of the first companies, possibly the first one, to generate new molecules using this new technique called generative adversarial networks–it's kind of AI imagination–and validate those molecules experimentally.

Why it matters: AI is a major growth force for American companies and "of paramount importance to maintaining the economic and national security of the United States" President Trump said in an executive order signed in February dubbed the "American AI Initiative." The big picture from Axios emerging tech reporter Kaveh Waddell: The U.S. had a head start in commercializing AI, thanks to unmatched talent and eager VC money. What's happening: In addition to the Chinese government allocating significant spending to AI, more new companies are being started in a raft of different countries and raising equity, analysts from CB Insights tell Axios in an email. Yes, but: The total amount of funding is still tilted heavily toward the U.S. -- with the exception of a handful of Chinese mega-companies like TikTok owner ByteDance, which is the top-funded AI startup in the world. The U.S. funding lead is likely to continue because of its concentration of AI experts.

Former secretary of state Henry Kissinger, former Google CEO Eric Schmidt, and Cornell University professor Daniel Huttenlocher worked together for three years to write a single article for the August 2019 issue of The Atlantic. In it, they set out to solve the "riddles" of artificial intelligence, which they call an "unstoppable revolution," but they only managed to mimic other AI sign-twirlers. Their conclusions read like an encyclopedia entry for "hyperbole": "The challenge of absorbing this new technology into the values and practices of the existing culture has no precedent. The most comparable event was the transition from the medieval to the modern period. AI software is more than technology, the authors contend. Its advent will change the meaning of truth as we know it: "The Enlightenment philosopher Immanuel Kant ascribed truth to the impact of the structure of the human mind on observed reality.

Outside of their ability to understand a company's fundamentals, one of the skills Raj Lala appreciates most about his portfolio managers is their ability to interpret body language. Sitting across from management teams before making a decision to either invest or divest from their companies, Lala, the CEO of Evolve ETFs, said his portfolio managers can learn a lot from simply reading the room. Maybe they spot a nervous twitch after a question on guidance or a CEO unable to make eye contact when responding to a question about declining revenues. That very human capability was at the forefront of Lala's mind when he was recently pitched on two types of artificial intelligence that he could incorporate into his portfolio management processes. And it's one of the reasons he said no. "I can't see AI getting to that point where it replaces human interaction and, quite honestly, I would say god bless our world if that's the case," Lala said.

Humans can manipulate Rubik's cubes with relative ease, but robots have historically had a tougher go of it. That's not to suggest there aren't exceptions to the rule -- an MIT invention recently solved a cube in a record-breaking 0.38 seconds -- but they typically involve purpose-built motors and controls. Encouragingly, a group of researchers at Tencent and the Chinese University of Hong Kong say they've designed a Rubik's cube manipulator that uses multi-fingered hands. "Dexterous in-hand manipulation is a key building block for robots to achieve human-level dexterity, and accomplish everyday tasks which involve rich contact," wrote the researchers. "Despite concerted progress, reliable multi-fingered dexterous hand manipulation has remained an open challenge, due to its complex contact patterns, high dimensional action space, and fragile mechanical structure."