Given a set of source data with pre-trained classification models, how can we fast and accurately select the most useful source data to improve the performance of a target task? We address the problem of measuring transferability for heterogeneous domains, where the source and the target data have different feature spaces and distributions. We propose Transmeter, a novel method to efficiently and accurately measure transferability of two datasets. Transmeter utilizes a pre-trained source classifier and a reconstruction loss to increase its efficiency and performance. Furthermore, Transmeter uses feature transformation layers, label-wise discriminators, and a mean distance loss to learn common representations for source and target domains. As a result, Transmeter and its variant give the most accurate performance in measuring transferability, while giving comparable running times compared to those of competitors.

We address two central notions of fairness in the literature of planning on nondeterministic fully observable domains. The first, which we call stochastic fairness, is classical, and assumes an environment which operates probabilistically using possibly unknown probabilities. The second, which is language-theoretic, assumes that if an action is taken from a given state infinitely often then all its possible outcomes should appear infinitely often (we call this state-action fairness). While the two notions coincide for standard reachability goals, they diverge for temporally extended goals. This important difference has been overlooked in the planning literature, and we argue has led to confusion in a number of published algorithms which use reductions that were stated for state-action fairness, for which they are incorrect, while being correct for stochastic fairness. We remedy this and provide an optimal sound and complete algorithm for solving state-action fair planning for LTL/LTLf goals, as well as a correct proof of the lower bound of the goal-complexity (our proof is general enough that it provides new proofs also for the no-fairness and stochastic-fairness cases). Overall, we show that stochastic fairness is better behaved than state-action fairness.

Minimum Routing Cost Clustered Tree Problem (CluMRCT) is applied in various fields in both theory and application. Because the CluMRCT is NP-Hard, the approximate approaches are suitable to find the solution for this problem. Recently, Multifactorial Evolutionary Algorithm (MFEA) has emerged as one of the most efficient approximation algorithms to deal with many different kinds of problems. Therefore, this paper studies to apply MFEA for solving CluMRCT problems. In the proposed MFEA, we focus on crossover and mutation operators which create a valid solution of CluMRCT problem in two levels: first level constructs spanning trees for graphs in clusters while the second level builds a spanning tree for connecting among clusters. To reduce the consuming resources, we will also introduce a new method of calculating the cost of CluMRCT solution. The proposed algorithm is experimented on numerous types of datasets. The experimental results demonstrate the effectiveness of the proposed algorithm, partially on large instances

The fact is quite evident that the world is witnessing a lack of top-tier AI talents across various regions of the globe. The technology is touching new boundaries on a regular basis, new advents and innovations are endless, all that is required is efficient talent and AI educated candidates to harness its potentials. However, a number of countries, realizing the growth potential and scope for artificial intelligence, have incorporated the professional curriculum to enhance the skills and talent across their industries. To understand the literacy of professionals in AI, JF Gagne's survey "Global AI Talent Report 2019" delved deep into the publications from 21 leading scientific conferences in the field of AI and analyzed the profiles of the authors. Secondly, it analyzed the results of several targeted LinkedIn searches, which depicted how many individuals are self-reporting that they have doctorates as well as the requisite skills in different regions around the world. According to the report, the countries with the highest number of high-impact researchers are the United States, China, the United Kingdom, Australia, and Canada.

For years, the Denver public school system worked with Video Insight, a Houston-based video management software company that centralized the storage of video footage used across its campuses. So when Panasonic acquired Video Insight, school officials simply transferred the job of updating and expanding their security system to the Japanese electronics giant. That meant new digital HD cameras and access to more powerful analytics software, including Panasonic's facial recognition, a tool the public school system's safety department is now exploring. Denver, where some activists are pushing for a ban on government use of facial recognition, is not alone. Mass shootings have put school administrators across the country on edge, and they're understandably looking at anything that might prevent another tragedy. Safety concerns have led some schools to consider artificial intelligence-enabled tools, including facial recognition software; AI that can scan video feeds for signs of brandished weapons; even analytics tools that warn when there's been suspicious movement in a usually-empty hallway.

On our sidewalks, in our skies, in our every store… Over the next decade, robots will enter the mainstream of retail. As countless robots work behind the scenes to stock shelves, serve customers, and deliver products to our doorstep, the speed of retail will accelerate. These changes are already underway. In this blog, we'll elaborate on how robots are entering the retail ecosystem. On August 3rd, 2016, Domino's Pizza introduced the Domino's Robotic Unit, or "DRU" for short.

Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption into unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications into critical domains where obtaining massive labelled data is prohibitively expensive. To enable downstream unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space. Random mapping is a theoretical proven approach to obtain approximately preserved distances. To well predict these random distances, the representation learner is optimised to learn genuine class structures that are implicitly embedded in the randomly projected space. Experimental results on 19 real-world datasets show our learned representations substantially outperform state-of-the-art competing methods in both anomaly detection and clustering tasks. Unsupervised representation learning aims at automatically extracting expressive feature representations from data without any manually labelled data. Due to the remarkable capability to learn semantic-rich features, deep neural networks have been becoming one widely-used technique to empower a broad range of machine learning tasks. One main issue with these deep learning techniques is that a massive amount of labelled data is typically required to successfully learn these expressive features. As a result, their transformation power is largely reduced for tasks that are unsupervised in nature, such as anomaly detection and clustering. This is also true to critical domains, such as healthcare and fintech, where collecting massive labelled data is prohibitively expensive and/or is impossible to scale. To bridge this gap, in this work we explore fully unsupervised representation learning techniques to enable downstream unsupervised learning methods on those critical domains. In recent years, many unsupervised representation learning methods (Mikolov et al., 2013a; Le & Mikolov, 2014; Misra et al., 2016; Lee et al., 2017; Gidaris et al., 2018) have been introduced, of which most are self-supervised approaches that formulate the problem as an annotation free pretext task.

Comparing business process variants using event logs is a common use case in process mining. Existing techniques for process variant analysis detect statistically-significant differences between variants at the level of individual entities (such as process activities) and their relationships (e.g. directly-follows relations between activities). This may lead to a proliferation of differences due to the low level of granularity in which such differences are captured. This paper presents a novel approach to detect statistically-significant differences between variants at the level of entire process traces (i.e. sequences of directly-follows relations). The cornerstone of this approach is a technique to learn a directly follows graph called mutual fingerprint from the event logs of the two variants. A mutual fingerprint is a lossless encoding of a set of traces and their duration using discrete wavelet transformation. This structure facilitates the understanding of statistical differences along the control-flow and performance dimensions. The approach has been evaluated using real-life event logs against two baselines. The results show that at a trace level, the baselines cannot always reveal the differences discovered by our approach, or can detect spurious differences.

Predictive process analytics has recently gained significant attention, and yet its successful adoption in organisations relies on how well users can trust the predictions of the underlying machine learning algorithms that are often applied and recognised as a `black-box'. Without understanding the rationale of the black-box machinery, there will be a lack of trust in the predictions, a reluctance to use the predictions, and in the worse case, consequences of an incorrect decision based on the prediction. In this paper, we emphasise the importance of interpreting the predictive models in addition to the evaluation using conventional metrics, such as accuracy, in the context of predictive process monitoring. We review existing studies on business process monitoring benchmarks for predicting process outcomes and remaining time. We derive explanations that present the behaviour of the entire predictive model as well as explanations describing a particular prediction. These explanations are used to reveal data leakages, assess the interpretability of features used by the model, and the degree of the use of process knowledge in the existing benchmark models. Findings from this exploratory study motivate the need to incorporate interpretability in predictive process analytics.

Australia Abstract Stability of recurrent models is closely linked with trainability, generalizability and in some applications, safety. Methods that train stable recurrent neural networks, however, do so at a significant cost to expressibility. We propose an implicit model structure that allows for a convex parametriza-tion of stable models using contraction analysis of nonlinear systems. Using these stability conditions we propose a new approach to model initialization and then provide a number of empirical results comparing the performance of our proposed model set to previous stable RNNs and vanilla RNNs. By carefully controlling stability in the model, we observe a significant increase in the speed of training and model performance. Keywords: System Identification, Contraction, Stability, Recurrent Neural Network, V anishing Gradient, Exploding Gradient, Nonlinear Systems, Echo State Network Notation Most of our notation is standard.