Parallel best-first search algorithms such as Hash Distributed A* (HDA*) distribute work among the processes using a global hash function. We analyze the search and communication overheads of state-of-the-art hash-based parallel best-first search algorithms, and show that although Zobrist hashing, the standard hash function used by HDA*, achieves good load balance for many domains, it incurs significant communication overhead since almost all generated nodes are transferred to a different processor than their parents. We propose Abstract Zobrist hashing, a new work distribution method for parallel search which, instead of computing a hash value based on the raw features of a state, uses a feature projection function to generate a set of abstract features which results in a higher locality, resulting in reduced communications overhead. We show that Abstract Zobrist hashing outperforms previous methods on search domains using hand-coded, domain specific feature projection functions. We then propose GRAZHDA*, a graph-partitioning based approach to automatically generating feature projection functions. GRAZHDA* seeks to approximate the partitioning of the actual search space graph by partitioning the domain transition graph, an abstraction of the state space graph. We show that GRAZHDA* outperforms previous methods on domain-independent planning.

Multi-Context Systems (MCS) are a powerful framework for interlinking possibly heterogeneous, autonomous knowledge bases, where information can be exchanged among knowledge bases by designated bridge rules with negation as failure. An acknowledged issue with MCS is inconsistency that arises due to the information exchange. To remedy this problem, inconsistency removal has been proposed in terms of repairs, which modify bridge rules based on suitable notions for diagnosis of inconsistency. In general, multiple diagnoses and repairs do exist; this leaves the user, who arguably may oversee the inconsistency removal, with the task of selecting some repair among all possible ones. To aid in this regard, we extend the MCS framework with preference information for diagnoses, such that undesired diagnoses are filtered out and diagnoses that are most preferred according to a preference ordering are selected. We consider preference information at a generic level and develop meta-reasoning techniques on diagnoses in MCS that can be exploited to reduce preference-based selection of diagnoses to computing ordinary subset-minimal diagnoses in an extended MCS. We describe two meta-reasoning encodings for preference orders: the first is conceptually simple but may incur an exponential blowup. The second is increasing only linearly in size and based on duplicating the original MCS. The latter requires nondeterministic guessing if a subset-minimal among all most preferred diagnoses should be computed. However, a complexity analysis of diagnoses shows that this is worst-case optimal, and that in general, preferred diagnoses have the same complexity as subset-minimal ordinary diagnoses. Furthermore, (subset-minimal) filtered diagnoses and (subset-minimal) ordinary diagnoses also have the same complexity.

Generative Adversarial Network (GAN) and its variants demonstrate state-of-the-art performance in the class of generative models. To capture higher dimensional distributions, the common learning procedure requires high computational complexity and large number of parameters. In this paper, we present a new generative adversarial framework by representing each layer as a tensor structure connected by multilinear operations, aiming to reduce the number of model parameters by a large factor while preserving the quality of generalized performance. To learn the model, we develop an efficient algorithm by alternating optimization of the mode connections. Experimental results demonstrate that our model can achieve high compression rate for model parameters up to 40 times as compared to the existing GAN.

This paper proposes a novel type of random forests called a denoising random forests that are robust against noises contained in test samples. Such noise-corrupted samples cause serious damage to the estimation performances of random forests, since unexpected child nodes are often selected and the leaf nodes that the input sample reaches are sometimes far from those for a clean sample. Our main idea for tackling this problem originates from a binary indicator vector that encodes a traversal path of a sample in the forest. Our proposed method effectively employs this vector by introducing denoising autoencoders into random forests. A denoising autoencoder can be trained with indicator vectors produced from clean and noisy input samples, and non-leaf nodes where incorrect decisions are made can be identified by comparing the input and output of the trained denoising autoencoder. Multiple traversal paths with respect to the nodes with incorrect decisions caused by the noises can then be considered for the estimation.

Nonnegative matrix factorization (NMF), a dimensionality reduction and factor analysis method, is a special case in which factor matrices have low-rank nonnegative constraints. Considering the stochastic learning in NMF, we specifically address the multiplicative update (MU) rule, which is the most popular, but which has slow convergence property. This present paper introduces on the stochastic MU rule a variance-reduced technique of stochastic gradient. Numerical comparisons suggest that our proposed algorithms robustly outperform state-of-the-art algorithms across different synthetic and real-world datasets.

We consider classifiers for high-dimensional data under the strongly spiked eigenvalue (SSE) model. We first show that high-dimensional data often have the SSE model. We consider a distance-based classifier using eigenstructures for the SSE model. We apply the noise reduction methodology to estimation of the eigenvalues and eigenvectors in the SSE model. We create a new distance-based classifier by transforming data from the SSE model to the non-SSE model. We give simulation studies and discuss the performance of the new classifier. Finally, we demonstrate the new classifier by using microarray data sets.

What has improved American lives most in the last 50 years? According to a Pew Research study reported this month, it's not civil rights (10 percent) or politics (2 percent): it's technology (42 percent). And yet, according to other studies, most Americans are wary of technology, especially in areas of automation (72 percent), or robotic caregivers (59 percent), or riding in driverless vehicles (56 percent), and even in using brain chip implants to augment the capabilities of healthy people (69 percent). Science fiction, however, is quickly becoming science fact--the future is the machine. This is leading many to argue that we need to anticipate the ethical questions now, rather than when it is too late.

While US technology giants such as Google, Facebook and Apple race to dominate the growing commercial market for artificial intelligence (AI), China Inc is digging deep to create a broad-based platform for this technology to drive the country's economic development. That was the consensus drawn from keynotes and panel discussions on Thursday at Finnovasia, the part of Hong Kong Fintech Week focusing on the future of AI in finance. Significant headway has been made on the mainland in AI, based on advances in computer-processing power, algorithms and data collection used by academic researchers and major internet companies such as Baidu, Alibaba Group Holding, Tencent Holdings and JD.com. In July, the State Council laid out goals to build a domestic AI industry worth nearly US$150 billion in the next few years, and to make the mainland an "innovation centre" in this field by 2030. "The US has better scientists doing research in AI … [But regarding] the union of AI and financial technology, China is leading and will continue to dominate in the future," Chan Ka-keung, adjunct professor of finance at the Hong Kong University of Science and Technology, said during a panel discussion on the mainland's rise in AI.

The consternation of radiologists about the impact of artificial intelligence is real--but so are the benefits of machine learning. Recent research showed that deep learning with a convolutional neural network (CNN) was successful in differentiating liver masses in CT. The retrospective study, published online Oct. 23 in Radiology, examined the diagnostic abilities of a deep learning method with a CNN. Researchers tested the CNN with 100 liver mass image sets from 2016, including 74 men and 26 women with the average age of 66 years old. "This preliminary study, which used 55, 536 image sets (1068 image sets augmented by a factor of 52) to obtain models, indicated that classifying liver masses into five categories can be accomplished with a high degree of accuracy by using a deep learning method with a CNN on dynamic contrast-enhanced CT images," wrote Koichiro Yasaka, MD, PhD, with the department of radiology at the University of Tokyo Hospital in Japan, and colleagues.

Ever since the beginning of industrial society, people have simultaneously marveled at the power of automation and lamented that human capabilities are being irredeemably devalued. Demanding better conditions and higher pay, textile workers in England smash machinery and set factories on fire. These workers will come to be known as Luddites, after their mythical leader, Ned Ludd, and the name will become a synonym for opponents or critics of technology. But it's a misnomer: this is a class protest more than a technological one. The stocking-frame machines the Luddites vandalize have been around since the 1600s.