Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale beyond the "single-expert, single-trainee" apprenticeship model. However, human domain experts often have difficulty describing their decision-making processes. We propose a new approach for capturing this decision-making process through counterfactual reasoning in pairwise comparisons. Our approach is model-free and does not require iterating through the state space. We demonstrate that this approach accurately learns multifaceted heuristics on a synthetic and real world data sets. We also demonstrate that policies learned from human scheduling demonstration via apprenticeship learning can substantially improve the efficiency of schedule optimization. We employ this human-machine collaborative optimization technique on a variant of the weapon-to-target assignment problem. We demonstrate that this technique generates optimal solutions up to 9.5 times faster than a state-of-the-art optimization algorithm.

Sequence-to-sequence (encoder-decoder) models with attention constitute a cornerstone of deep learning research, as they have enabled unprecedented sequential data modeling capabilities. This effectiveness largely stems from the capacity of these models to infer salient temporal dynamics over long horizons; these are encoded into the obtained neural attention (NA) distributions. However, existing NA formulations essentially constitute point-wise selection mechanisms over the observed source sequences; that is, attention weights computation relies on the assumption that each source sequence element is independent of the rest. Unfortunately, although convenient, this assumption fails to account for higher-order dependencies which might be prevalent in real-world data. This paper addresses these limitations by leveraging Quantum-Statistical modeling arguments. Specifically, our work broadens the notion of NA, by attempting to account for the case that the NA model becomes inherently incapable of discerning between individual source elements; this is assumed to be the case due to higher-order temporal dynamics. On the contrary, we postulate that in some cases selection may be feasible only at the level of pairs of source sequence elements. To this end, we cast NA into inference of an attention density matrix (ADM) approximation. We derive effective training and inference algorithms, and evaluate our approach in the context of a machine translation (MT) application. We perform experiments with challenging benchmark datasets. As we show, our approach yields favorable outcomes in terms of several evaluation metrics.

In this paper, we show how unsupervised sense representations can be used to improve hypernymy extraction. We present a method for extracting disambiguated hypernymy relationships that propagates hypernyms to sets of synonyms (synsets), constructs embeddings for these sets, and establishes sense-aware relationships between matching synsets. Evaluation on two gold standard datasets for English and Russian shows that the method successfully recognizes hypernymy relationships that cannot be found with standard Hearst patterns and Wiktionary datasets for the respective languages.

This paper addresses the question of identifying the time-window in short-term past from which the information regarding the future occupant's window opening actions and resulting window states in buildings can be predicted. The addressed sequence duration was in the range between 30 and 240 time-steps of indoor climate data, where the applied temporal discretization was one minute. For that purpose, a deep neural network is trained to predict the window states, where the input sequence duration is handled as an additional hyperparameter. Eventually, the relationship between the prediction accuracy and the time-lag of the predicted window state in future is analyzed. The results pointed out, that the optimal predictive performance was achieved for the case where 60 time-steps of the indoor climate data were used as input. Additionally, the results showed that very long sequences (120-240 time-steps) could be addressed efficiently, given the right hyperprameters. Hence, the use of the memory over previous hours of high-resolution indoor climate data did not improve the predictive performance, when compared to the case where 30/60 minutes indoor sequences were used. The analysis of the prediction accuracy in the form of F1 score for the different time-lag of future window states dropped from 0.51 to 0.27, when shifting the prediction target from 10 to 60 minutes in future.

Ever increasing number of Android malware, has always been a concern for cybersecurity professionals. Even though plenty of anti-malware solutions exist, a rational and pragmatic approach for the same is rare and has to be inspected further. In this paper, we propose a novel two-set feature selection approach based on Rough Set and Statistical Test named as RSST to extract relevant system calls. To address the problem of higher dimensional attribute set, we derived suboptimal system call space by applying the proposed feature selection method to maximize the separability between malware and benign samples. Comprehensive experiments conducted on a dataset consisting of 3500 samples with 30 RSST derived essential system calls resulted in an accuracy of 99.9%, Area Under Curve (AUC) of 1.0, with 1% False Positive Rate (FPR). However, other feature selectors (Information Gain, CFsSubsetEval, ChiSquare, FreqSel and Symmetric Uncertainty) used in the domain of malware analysis resulted in the accuracy of 95.5% with 8.5% FPR. Besides, empirical analysis of RSST derived system calls outperform other attributes such as permissions, opcodes, API, methods, call graphs, Droidbox attributes and network traces.

Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning tasks, while making progress towards constructing more interpretable CNNs. For supervised learning, we demonstrate that the early layers of CNNs do not necessarily need to be learned, and can be replaced with a scattering network instead. Indeed, using hybrid architectures, we achieve the best results with predefined representations to-date, while being competitive with end-to-end learned CNNs. Specifically, even applying a shallow cascade of small-windowed scattering coefficients followed by 1$\times$1-convolutions results in AlexNet accuracy on the ILSVRC2012 classification task. Moreover, by combining scattering networks with deep residual networks, we achieve a single-crop top-5 error of 11.4% on ILSVRC2012. Also, we show they can yield excellent performance in the small sample regime on CIFAR-10 and STL-10 datasets, exceeding their end-to-end counterparts, through their ability to incorporate geometrical priors. For unsupervised learning, scattering coefficients can be a competitive representation that permits image recovery. We use this fact to train hybrid GANs to generate images. Finally, we empirically analyze several properties related to stability and reconstruction of images from scattering coefficients.

When modeling real world domains we have to deal with information that is incomplete or that comes from sources with different trust levels. This motivates the need for managing uncertainty in the Semantic Web. To this purpose, we introduced a probabilistic semantics, named DISPONTE, in order to combine description logics with probability theory. The probability of a query can be then computed from the set of its explanations by building a Binary Decision Diagram (BDD). The set of explanations can be found using the tableau algorithm, which has to handle non-determinism. Prolog, with its efficient handling of non-determinism, is suitable for implementing the tableau algorithm. TRILL and TRILLP are systems offering a Prolog implementation of the tableau algorithm. TRILLP builds a pinpointing formula, that compactly represents the set of explanations and can be directly translated into a BDD. Both reasoners were shown to outperform state-of-the-art DL reasoners. In this paper, we present an improvement of TRILLP, named TORNADO, in which the BDD is directly built during the construction of the tableau, further speeding up the overall inference process. An experimental comparison shows the effectiveness of TORNADO. All systems can be tried online in the TRILL on SWISH web application at http://trill.ml.unife.it/.

The rise of machines, robots and algorithms in the workplace stands to create almost double the number of jobs for the global economy by the middle of the next decade than it puts at risk of being replaced. According to the World Economic Forum (WEF), about 133m jobs globally could be created with the help of rapid technological advances in the workplace over the next decade, compared with 75m that could be displaced. The findings will go some way towards assuaging fears that the rise of the robot economy could cost millions of workers their jobs, with widespread ramifications for pay, living standards and inequality across developed nations. The WEF report suggests new technologies have the capacity to both disrupt and create new ways of working, similar to previous periods of economic history such as the Industrial Revolution, when the advent of steam power and then electricity helped spur the creation of new jobs and the development of the middle class. The findings, from a survey of company executives representing 15 million workers in 20 different nations by the organiser of the annual Davos gathering of business leaders and politicians, does, however, warn of risks posed by automation.

It's obvious that it takes years to train doctors, especially those who handle serious and complicated medical issues – pathologists, cardiologists, dermatologists and the rest, that's why there's always a shortage of these lifesaving experts. Thanks to artificial intelligence because now, machines can be trained to help fill that shortage. In fact, already, we have AI tools that can diagnose pneumonia, fungi, depression and certain eye infections -- all with an average accuracy rate of over 92 percent. And you know what, the list is expanding further! Chinese researchers have managed to develop a new system that diagnoses prostate cancer, as accurately as pathologists do.

Big pharma is taking an AI-first approach. Apple is revolutionizing clinical studies. We look at the top artificial intelligence trends reshaping healthcare. Healthcare is emerging as a prominent area for AI research and applications. And nearly every area across the industry will be impacted by the technology's rise. Image recognition, for example, is revolutionizing diagnostics. Recently, Google DeepMind's neural networks matched the accuracy of medical experts in diagnosing 50 sight-threatening eye diseases. Even pharma companies are experimenting with deep learning to design new drugs. For example, Merck partnered with startup Atomwise and GlaxoSmithKline is partnering with Insilico Medicine.