The task of recognizing goals and plans from missing and full observations can be done efficiently by using automated planning techniques. In many applications, it is important to recognize goals and plans not only accurately, but also quickly. To address this challenge, we develop novel goal recognition approaches based on planning techniques that rely on planning landmarks. In automated planning, landmarks are properties (or actions) that cannot be avoided to achieve a goal. We show the applicability of a number of planning techniques with an emphasis on landmarks for goal and plan recognition tasks in two settings: (1) we use the concept of landmarks to develop goal recognition heuristics; and (2) we develop a landmark-based filtering method to refine existing planning-based goal and plan recognition approaches. These recognition approaches are empirically evaluated in experiments over several classical planning domains. We show that our goal recognition approaches yield not only accuracy comparable to (and often higher than) other state-of-the-art techniques, but also substantially faster recognition time over such techniques.

Assessing whether an agent has abandoned a goal or is actively pursuing it is important when multiple agents are trying to achieve joint goals, or when agents commit to achieving goals for each other. Making such a determination for a single goal by observing only plan traces is not trivial as agents often deviate from optimal plans for various reasons, including the pursuit of multiple goals or the inability to act optimally. In this article, we develop an approach based on domain independent heuristics from automated planning, landmarks, and fact partitions to identify sub-optimal action steps - with respect to a plan - within a plan execution trace. Such capability is very important in domains where multiple agents cooperate and delegate tasks among themselves, e.g. through social commitments, and need to ensure that a delegating agent can infer whether or not another agent is actually progressing towards a delegated task. We demonstrate how an agent can use our technique to determine - by observing a trace - whether an agent is honouring a commitment. We empirically show, for a number of representative domains, that our approach infers sub-optimal action steps with very high accuracy and detects commitment abandonment in nearly all cases.

Nonlinear interactions in the dendritic tree play a key role in neural computation. Nevertheless, modeling frameworks aimed at the construction of large-scale, functional spiking neural networks tend to assume linear, current-based superposition of post-synaptic currents. We extend the theory underlying the Neural Engineering Framework to systematically exploit nonlinear interactions between the local membrane potential and conductance-based synaptic channels as a computational resource. In particular, we demonstrate that even a single passive distal dendritic compartment with AMPA and GABA-A synapses connected to a leaky integrate-and-fire neuron supports the computation of a wide variety of multivariate, bandlimited functions, including the Euclidean norm, controlled shunting, and non-negative multiplication. Our results demonstrate that, for certain operations, the accuracy of dendritic computation is on a par with or even surpasses the accuracy of an additional layer of neurons in the network. These findings allow modelers to construct large-scale models of neurobiological systems that closer approximate network topologies and computational resources available in biology. Our results may inform neuromorphic hardware design and could lead to a better utilization of resources on existing neuromorphic hardware platforms.

In this paper, we consider the problem of learning a (first-order) theorem prover where we use a representation of beliefs in mathematical claims instead of a proof system to search for proofs. The inspiration for doing so comes from the practices of human mathematicians where a proof system is typically used after the fact to justify a sequence of intuitive steps obtained by "plausible reasoning" rather than to discover them. Towards this end, we introduce a probabilistic representation of beliefs in first-order statements based on first-order distributive normal forms (dnfs) devised by the philosopher Jaakko Hintikka. Notably, the representation supports Bayesian update and does not enforce that logically equivalent statements are assigned the same probability---otherwise, we would end up in a circular situation where we require a prover in order to assign beliefs. We then examine (1) conjecturing as (statistical) model selection and (2) an alternating-turn proving game amenable (in principle) to self-play training to learn a prover that is both complete in the limit and sound provided that players maintain "reasonable" beliefs. Dnfs have super-exponential space requirements so the ideas in this paper should be taken as conducting a thought experiment on "learning to prove". As a step towards making the ideas practical, we will comment on how abstractions can be used to control the space requirements at the cost of completeness.

Large-scale Machine Learning (ML) algorithms are often iterative, using repeated read-only data access and I/O-bound matrix-vector multiplications. Hence, it is crucial for performance to fit the data into single-node or distributed main memory to enable fast matrix-vector operations. General-purpose compression struggles to achieve both good compression ratios and fast decompression for block-wise uncompressed operations. Therefore, we introduce Compressed Linear Algebra (CLA) for lossless matrix compression. CLA encodes matrices with lightweight, value-based compression techniques and executes linear algebra operations directly on the compressed representations. We contribute effective column compression schemes, cache-conscious operations, and an efficient sampling-based compression algorithm. Our experiments show good compression ratios and operations performance close to the uncompressed case, which enables fitting larger datasets into available memory. We thereby obtain significant end-to-end performance improvements. Large-scale ML leverages large data collections to find interesting patterns or build robust predictive models.7 Applications range from traditional regression, classification, and clustering to user recommendations and deep learning for unstructured data. The labeled data required to train these ML models is now abundant, thanks to feedback loops in data products and weak supervision techniques. Many ML systems exploit data-parallel frameworks such as Spark20 or Flink2 for parallel model training and scoring on commodity hardware. It remains challenging, however, to train ML models on massive labeled data sets in a cost-effective manner.

Samuel Greengard is an author and journalist based in West Linn, OR, USA.

When Tavis Rudd decided to build a system that would allow him to write computer code using his voice, he was driven by necessity. In 2010, he tore his rotator cuffwhile rock-climbing, forcing him to quit climbing while the injury healed. Rather than sitting idle, he poured more of his energy into his work as a self-employed computer programmer. "I'd get in the zone and just go for hours," he says. Whether it was the increased time pounding away at a keyboard or the lack of other exercise, Rudd eventually developed a repetitive strain injury (RSI) that caused his outer fingers to go numb and cold, leaving him unable to type/code without pain.

At the beginning of December last year, a committee set up by the U.S. National Academies of Sciences, Engineering, and Medicine said it had come to the conclusion a viable quantum computer with the ability to break ciphers based on today's encryption algorithms is a decade or more away, but they are coming. Committee chair Mark Horowitz said he and his colleagues could see no fundamental reason, in principle, why a functional quantum computer could not ever be built. When they do finally arrive, quantum computers pose a number of problems for computer scientists when it comes to determining whether they work as expected. Quantum computers can make use of the property of superposition: where the bits in a register in the machine do not exist in a single known state, but in a combination of states. Each state has a finite probability of being the one recorded when the register is read and the superposition collapses.

Demand for more powerful big data analytics solutions has spurred the development of novel programming models, abstractions, and platforms for next-generation systems. For these problems, a complete solution would address data wrangling and processing, and it would support analytics over data of any modality or scale. It would support a wide array of machine learning algorithms, but also provide primitives for building new ones. It would be customizable, scale to vast volumes of data, and map to modern multicore, GPU, coprocessor, and compute cluster hardware. In pursuit of these goals, novel techniques and solutions are being developed by machine learning researchers,4,6,7 in the database and distributed systems research communities,2,5,8 and by major players in industry.1,3

Study author Gopala Anumanchipalli holds an example of the gadget that could literally give voice to the voiceless. Trapped inside their bodies, stroke patients may be able to think – but not speak. But now, according to a new study, a device could one day literally give a voice to the voiceless. "For the first time, this study demonstrates that we can generate entire spoken sentences based on an individual's brain activity," said study lead author Edward Chang, a professor of neurological surgery at the University of California at San Francisco. In fact, he said the technology could potentially restore the voices of people who have lost the ability to speak due to paralysis and other forms of neurological damage such as from ALS (Lou Gehrig's Disease).