The deep learning algorithms of artificial intelligence can identify patterns that help inventors think laterally, make connections between nonobvious ideas, pinpoint hidden invention features, and exploit new science and technology-based opportunities. "To invent, you need a good imagination and a pile of junk." So said Thomas Edison, America's most prolific inventor. Yet the march of technology is now changing the great man's inventive equation: powerful algorithmic advisory systems are now giving inventors far more fertile imaginations, even if they don't have very much of one themselves. After being fed vast datasets of information on a field of inventive endeavor, deep learning algorithms identify patterns that help inventors think laterally, make connections between nonobvious ideas, pinpoint hidden invention features that rivals have missed, and exploit new science and technology-based opportunities from, say, patents and journals.

We present a corpus and approach to deduce the difficulty of questions asked in a reading comprehension test. A feature-driven model is designed that associates each question with a difficulty level. This would eliminate the laborious task of manually annotating questions in a computerized testing environment. Experiments performed on our corpus show that our model can classify questions with a micro F-score of 0.68.

Supervised classification is the most active and emerging research trends in today's scenario. In this view, Artificial Neural Network (ANN) techniques have been widely employed and growing interest to the researchers day by day. ANN training aims to find the proper setting of parameters such as weights ($\textbf{W}$) and biases ($b$) to properly classify the given data samples. The training process is formulated in an error minimization problem which consists of many local optima in the search landscape. In this paper, an enhanced Particle Swarm Optimization is proposed to minimize the error function for classifying real-life data sets. A stability analysis is performed to establish the efficiency of the proposed method for improving classification accuracy. The performance measurement such as confusion matrix, $F$-measure and convergence graph indicates the significant improvement in the classification accuracy.

Machine Learning is transitioning from an art and science into a technology available to every developer. In the near future, every application on every platform will incorporate trained models to encode data-based decisions that would be impossible for developers to author. This presents a significant engineering challenge, since currently data science and modeling are largely decoupled from standard software development processes. This separation makes incorporating machine learning capabilities inside applications unnecessarily costly and difficult, and furthermore discourage developers from embracing ML in first place. In this paper we present ML .NET, a framework developed at Microsoft over the last decade in response to the challenge of making it easy to ship machine learning models in large software applications. We present its architecture, and illuminate the application demands that shaped it. Specifically, we introduce DataView, the core data abstraction of ML .NET which allows it to capture full predictive pipelines efficiently and consistently across training and inference lifecycles. We close the paper with a surprisingly favorable performance study of ML .NET compared to more recent entrants, and a discussion of some lessons learned.

This paper presents the results of an automated volatile organic compound (VOC) classification process implemented by embedding a machine learning algorithm into an Arduino Uno board. An electronic nose prototype is constructed to detect VOCs from three different fruits. The electronic nose is constructed using an array of five tin dioxide (SnO2) gas sensors, an Arduino Uno board used as a data acquisition section, as well as an intelligent classification module by embedding an approach function which receives data signals from the electronic nose. For the intelligent classification module, a training algorithm is also implemented to create the base of a portable, automated, fast-response, and economical electronic nose device. This solution proposes a portable system to identify and classify VOCs without using a personal computer (PC). Results show an acceptable precision for the embedded approach in comparison with the performance of a toolbox used in a PC. This constitutes an embedded solution able to recognize VOCs in a reliable way to create application products for a wide variety of industries, which are able to classify data acquired by an electronic nose, as VOCs. With this proposed and implemented algorithm, a precision of 99% for classification was achieved into the embedded solution.

We consider an agent who is involved in a Markov decision process and receives a vector of outcomes every round. Her objective is to maximize a global concave reward function on the average vectorial outcome. The problem models applications such as multi-objective optimization, maximum entropy exploration, and constrained optimization in Markovian environments. In our general setting where a stationary policy could have multiple recurrent classes, the agent faces a subtle yet consequential trade-off in alternating among different actions for balancing the vectorial outcomes. In particular, stationary policies are in general sub-optimal. We propose a no-regret algorithm based on online convex optimization (OCO) tools (Agrawal and Devanur 2014) and UCRL2 (Jaksch et al. 2010). Importantly, we introduce a novel gradient threshold procedure, which carefully controls the switches among actions to handle the subtle trade-off. By delaying the gradient updates, our procedure produces a non-stationary policy that diversifies the outcomes for optimizing the objective. The procedure is compatible with a variety of OCO tools.

Argument mining is a rising area of Natural Language Pro- cessing (NLP) concerned with the automatic recognition and interpretation of argument components and their relations. Neural models are by now mature technologies to be ex- ploited for automating the argument mining tasks, despite the issue of data sparseness. This could ease much of the man- ual effort involved in these tasks, taking into account hetero- geneous types of texts and topics. In this work, we evaluate different attention mechanisms applied over a state-of-the-art architecture for sequence labeling. We assess the impact of different flavors of attention in the task of argument compo- nent detection over two datasets: essays and legal domain. We show that attention not models the problem better but also supports interpretability.

In a multiagent system or MAS, due to agent interactions, the agents as a group may make decisions that none of them would make alone; this phenomenon is called emergence. Emergence is characterized by an unanticipated system behavior caused by nonlinear interactions. This paper detects such emergence in a MAS by analyzing agent behaviors across two simple strategies. In the first strategy, agents make decisions based on the local information; in the second strategy, agents make decisions based on global information provided via communication. The proposed method identifies when and how nonlinear interactions cause behavior change, and quantitatively defines emergence based on the change in team performance. It then proves several theorems about emergence in a MAS. It also explores several emergence-related factors like the communication cost and the reward gap quantitatively. Experimental results on several benchmarks demonstrate the promising performance of the proposed framework in detecting emergence in a MAS.

We present a novel technique for pre-processing files that can improve file compression rates of existing general purpose lossless file compression algorithms, particularly for files that these algorithms perform poorly on. The elementary cellular automata (CA) pre-processing technique involves finding a CA state that can be used to transform a file into a format that is more amenable to compression than the original file format. This technique is applicable to multiple file types and may be used to enhance multiple compression algorithms. Evaluation on files that we generated, as well as samples selected from online text repositories, finds that the CA pre-processing technique improves compression rates by up to 4% and shows promising results for assisting in compressing data that typically induce worst-case behavior in standard compression algorithms.

Recently, there has been much attention on tools and techniques for visualizing and acquiring new knowledge and insights. In the VAST 2018 competition, one of the challenges is to discover the fraudulent group of employees at Kasios, a furniture manufacturing company. In this work, we use a graph-based approach that analyzes the data for suspicious employee activities at Kasios. Graph based approaches enable one to handle rich contextual data and provide a deeper understanding of data due to the ability to discover patterns in databases that are not easily found using traditional query or statistical tools. We focus on graph based knowledge discovery in structural data to mine for interesting patterns and anomalies. Our approach first reports the normative patterns in the data, and then discovers any anomalous patterns associated with the previously discovered patterns. For visualizing the suspicious patterns, we also use the enterprise graph database Neo4j. Neo4j Browser provides a way to visualize graph structures.