Abstract: Adaptive network-based fuzzy inference system (ANFIS), is a suitable technique for predicting the behavior of systems. In recent years, the capabilities of ANFIS in controlling nonlinear systems, has been studied by researchers. In this work, ability of ANFIS controller to stabilize the multi-link inverted pen-dulum-cart system is presented. The inverted pendulum on a cart system is a sys-tem with unstable and nonlinear behavior. Different types of inverted pendulum including single link inverted pendulum(SIP), double link inverted pendu-lum(DIP), triple link inverted pendulum(TIP) are subject of this paper. Training can be considered the most important and challenging part in design of ANFIS controller. To solve this problem, linear quadratic regulator(LQR) and linear model of inverted pendulum system are used, in a way that data including state variables are reduced to two variables, error and variation of error and are used for training of ANFIS. The most important section in designing of LQR is ap-propriate determination of Q and R matrices and consequently control gain matrix K so that it can meet the desired system characteristics such as settling time, over-shoot, …. The classic way for determination of these matrices, is trial and error approach that can be very time consuming and frustrating in some cases in addi-tion there is no guarantee to find the best possible solutions. To overcome this problem, Optimization algorithms have been used. Two Powerful optimization algorithms including genetic algorithm and particle swarm optimization algorithm are used and their results have been compared. In the end, the obtained results in MATLAB/SIMULINK environment show that the proposed ANFIS controller has an excellent ability to stabilize nonlinear multi-link inverted pendulum system in a very short time. The results associated with adding noise at the input of the system are provided in the final section of this paper which confirm that the pro-posed ANFIS controller is robust and effective.

Abstract: We consider a Cartesian decomposition of datasets, i.e. finding datasets such that their unordered Cartesian product yields the source set, and some natural generalization of this decomposition. In terms of relational databases, this means reversing the SQL CROSS JOIN and INNER JOIN operators (the last is equipped with a test verifying the equality of a table’s attribute to another table’s attribute). First we outline a polytime algorithm for computing the Cartesian decomposition. Then we describe a polytime algorithm for computing a generalized decomposition based on the Cartesian decomposition. Some applications and relating problems are discussed.

Abstract: Manifold learning is a main stream research track used for dimensionality reduction as a method to select features. Many variants have been proposed with good performance. In this paper, we present a novel graph-based supervised learning framework for image classification. It takes the advantage of graph embedding to improve the recognition accuracy. The proposed method is tested on four benchmark datasets of different types including scene, face and object. The experimental results demonstrate the effectiveness of the proposed algorithm by the comparison with other tested algorithms.

Abstract: Relation classification is one of the most important topics in Natural Language Processing (NLP) which could help mining structured facts from text and constructing knowledge graph. Although deep neural network models have achieved improved performance in this task, the state-of-the-art methods still suffer from the scarce training data and the overfitting problem. In order to solve this problem, we adopt the adversarial training framework to improve the robustness and generalization of the relation classifier. In this paper, we construct a bidirectional recurrent neural network as the relation classifier, and append word-level attention to the input sentence. Our model is an end-to-end framework without the use of any features derived from pre-trained NLP tools. In experiments, our model achieved higher F1-score and better robustness than comparative methods.

Abstract: Given a microblog post and a topic, it is an important task to judge the sentiment towards that topic: positive or negative, and has important theoretical and application value in the public opinion analysis, personalized recommendation, product comparison analysis, prevention of terrorist attacks, etc. Because of the short and irregular messages as well as containing multifarious features such as emoticons, and sentiment of a microblog post is closely related to its topic, most existing approaches cannot perfectly achieve cooperating analysis of topic and sentiment of messages, and even cannot know what factors actually determined the sentiment towards that topic. To address the issues, MB-LDA model and attention network are applied to Bi-RNN for topic-based microblog polarity classification. Our cascaded model has three distinctive characteristics: (i) a strong relationship between topic and its sentiment is considered; (ii) the factors that affect the topic’s sentiment are identified, and the degree of influence of each factor can be calculated; (iii) the synchronized detection of the topic and its sentiment in microblog is achieved. Extensive experiments show that our cascaded model outperforms state-of-the-art unsupervised approach JST and supervised approach SSA-ST significantly in terms of sentiment classification accuracy and F1-Measure.

Abstract: The existing pedestrian detection methods are still challenging under abrupt illumination, different human shape, and cluttered backgrounds. In this contribution, we suggest a novel method to handle the above detection failures. On account of the fact that the potential of features are different and a single feature cannot extract the comprehensive information and human appearance can be better acquired by combinations of efficacious features, we combine HOG, LBP, and Haar-like features. Thus, the proposed method contains the edge, texture information, and local shape information. It should be mentioned that there has not been a method based on combination of these three features yet. After feature combination, linear SVM classifier is used to detect pedestrian images from non-pedestrian. In experiments, INRIA dataset, Daimler dataset, and ETH dataset are adopted as the training and testing sets. Each dataset was recorded in various environments, resolution, and background occlusion. As a result, employing three various datasets can help not only further enrich our data but also scrutinize the robustness and precision of the proposed method in more depth. The substantial experimental result indicated that the proposed scheme outperformed the state of the art methods in terms of the accuracy with comparable computational time.

Abstract: Recommending the best and optimal content to user is the essential part of digital space activities and online user interactions. For example, we like to know what items should be sent to a user, what promotion is the best one for a user, what web design would fit a specific user, what ad a user would be more susceptible to or what creative cloud package is more suitable to a specific user. In this work, we use deep learning (autoencoders) to create a new model for this purpose. The previous art includes using Autoencoders for numerical features only and we extend the application of autoencoders to non-numerical features. Our approach in coming up with recommendation is using “matrix comple-tion” approach which is the most efficient and direct way of finding and evaluating content recommendation.

Abstract: AI and machine learning are mathematical modeling methods for learning from data and producing intelligent models based on this learning. The data these models need to deal with, is normally a mixed of data type where both numerical (continuous) variables and categorical (non-numerical) data types. Most models in AI and machine learning accept only numerical data as their input and thus, standardization of mixed data into numerical data is a critical step when applying machine learning models. Having data in the standard shape and format that models require often a time consuming, nevertheless very significant step of the process.

Abstract: The world of AI and Machine Learning is the world of data and learning from data so the insights could be used for analysis and prediction. Almost all data sets are of mixed variable types as they may be quantitative (numerical) or qualitative (categorical). The problem arises from the fact that a long list of methods in Machine Learning such as “multiple regression”, “logistic regression”, “k-means clustering”, and “support vector machine”, all to be as examples of such models, designed to deal with numerical data type only. Though the data, that need to be analyzed and learned from, is almost always, a mixed data type and thus, standardization step must be undertaken for all these data sets. The standardization process involves the conversion of qualitative (categorical) data into numerical data type.

Abstract: Latent Dirichlet Allocation (LDA) is a statistical technique for topic modeling. Since it is very computationally demanding, its parallelization has garnered considerable interest. In this paper, we systematically analyze the data access patterns for LDA and devise suitable algorithmic adaptations and parallelization strategies for GPUs. Experiments on large-scale datasets show the effectiveness of the new parallel implementation on GPUs.

Abstract: We develop a reinforcement learning based search assistant which can assist users through a sequence of actions to enable them realize their intent. Our approach caters to subjective search where user is seeking digital assets such as images which is fundamentally different from the tasks which have objective and limited search modalities. Labeled conversational data is generally not available in such search tasks, to counter this problem we propose a stochastic virtual user which impersonates a real user for training and obtaining bootstrapped agent. We develop A3C algorithm based context preserving architecture to train agent and evaluate performance on average rewards obtained by the agent while interacting with virtual user. We evaluated our system with actual humans who believed that it helped in driving their search forward with appropriate actions without being repetitive while being more engaging and easy to use compared to conventional search interface.