Using perspective taking to learn from ambiguous demonstrations

This paper addresses an important issue in learning from demonstrations that are provided by “naïve” human teachers—people who do not have expertise in the machine learning algorithms used by the robot. We therefore entertain the possibility that, whereas the average human user may provide sensible demonstrations from a human’s perspective, these same demonstrations may be insufficient, incomplete, ambiguous, or otherwise “flawed” from the perspective of the training set needed by the learning algorithm to generalize properly. To address this issue, we present a system where the robot is modeled as a socially engaged and socially cognitive learner. We illustrate the merits of this approach through an example where the robot is able to correctly learn from “flawed” demonstrations by taking the visual perspective of the human instructor to clarify potential ambiguities.     

Using naïve physics for odor localization in a cluttered indoor environment

This paper describes current progress of a project, which uses naïve physics to enable a robot to perform efficient odor localization. Odor localization is the problem of finding the source of an odor or other volatile chemical. Most localization methods require the robot to follow the odor plume along its entire length, which is time consuming and may be especially difficult in a cluttered environment. These drawbacks are significant in light of potential applications such as search and rescue operations in damaged buildings. In this project a map of the robot’s environment was used, together with a naïve physics model of airflow, to predict the pattern of air movement. The robot then used the airflow pattern to reason about the probable location of the odor source. This approach, based on naïve physics, has successfully located odor sources in a simplified environment. This demonstrates that naïve physics can be used to assist odor localization operations and indicates that similar techniques have great potential for allowing a robot operating in an unstructured environment to reason about its surroundings. This paper presents details of the naïve physical model of airflow, the reasoning system, the experimental equipment, and results of practical odor source localization experiments.     

A case-study on naïve labelling for the nearest mean and the linear discriminant classifiers

The abundance of unlabelled data alongside limited labelled data has provoked significant interest in semi-supervised learning methods. “Naïve labelling” refers to the following simple strategy for using unlabelled data in on-line classification. A new data point is first labelled by the current classifier and then added to the training set together with the assigned label. The classifier is updated before seeing the subsequent data point. Although the danger of a run-away classifier is obvious, versions of naïve labelling pervade in on-line adaptive learning. We study the asymptotic behaviour of naïve labelling in the case of two Gaussian classes and one variable. The analysis shows that if the classifier model assumes correctly the underlying distribution of the problem, naïve labelling will drive the parameters of the classifier towards their optimal values. However, if the model is not guessed correctly, the benefits are outweighed by the instability of the labelling strategy (run-away behaviour of the classifier). The results are based on exact calculations of the point of convergence, simulations, and experiments with 25 real data sets. The findings in our study are consistent with concerns about general use of unlabelled data, flagged up in the recent literature.     

Goal emulation and planning in perceptual space using learned affordances

In this paper, we show that through self-interaction and self-observation, an anthropomorphic robot equipped with a range camera can learn object affordances and use this knowledge for planning. In the first step of learning, the robot discovers commonalities in its action-effect experiences by discovering effect categories. Once the effect categories are discovered, in the second step, affordance predictors for each behavior are obtained by learning the mapping from the object features to the effect categories. After learning, the robot can make plans to achieve desired goals, emulate end states of demonstrated actions, monitor the plan execution and take corrective actions using the perceptual structures employed or discovered during learning. We argue that the learning system proposed shares crucial elements with the development of infants of 7–10 months age, who explore the environment and learn the dynamics of the objects through goal-free exploration. In addition, we discuss goal emulation and planning in relation to older infants with no symbolic inference capability and non-linguistic animals which utilize object affordances to make action plans.     

Turnover Prediction in a Call Center: Behavioral Evidence of Loss Aversion using Random Forest and Naïve Bayes Algorithms

It is well known that call centers suffer from high levels of employee turnover; however, call centers are services that have excellent operational records of telemarketing activities performed by each employee. With this information, we propose to use the Random Forest and the naïve Bayes algorithms to build classifiers and predict turnover of the sales agents. The results of 2407 sales agents’ operational performance records showed that, although the naïve Bayes is much simpler than Random Forest, both classifiers performed similarly, achieving interesting accuracy rates in turnover prediction. Moreover, evidence was found that incorporating performance differences over time increases significantly the accuracy of the predictive models up to 85%, with the naïve Bayes being quite competitive with the Random Forest classifier when the amount of information is increased. The results obtained in this study could be useful for management decision-making to monitor and identify potential turnover due to poor performance, and therefore, to take a preventive action.     

Shilling attack detection utilizing semi-supervised learning method for collaborative recommender system

Collaborative filtering (CF) technique is capable of generating personalized recommendations. However, the recommender systems utilizing CF as their key algorithms are vulnerable to shilling attacks which insert malicious user profiles into the systems to push or nuke the reputations of targeted items. There are only a small number of labeled users in most of the practical recommender systems, while a large number of users are unlabeled because it is expensive to obtain their identities. In this paper, Semi-SAD, a new semi-supervised learning based shilling attack detection algorithm is proposed to take advantage of both types of data. It first trains a naïve Bayes classifier on a small set of labeled users, and then incorporates unlabeled users with EM-λ to improve the initial naïve Bayes classifier. Experiments on MovieLens datasets are implemented to compare the efficiency of Semi-SAD with supervised learning based detector and unsupervised learning based detector. The results indicate that Semi-SAD can better detect various kinds of shilling attacks than others, especially against obfuscated and hybrid shilling attacks.     

Socially guided intrinsic motivation for robot learning of motor skills

This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our algorithmic architecture, called SGIM-D, allows efficient learning of high-dimensional continuous sensorimotor inverse models in robots, and in particular learns distributions of parameterised motor policies that solve a corresponding distribution of parameterised goals/tasks. This is made possible by the technical integration of imitation learning techniques within an algorithm for learning inverse models that relies on active goal babbling. After reviewing social learning and intrinsic motivation approaches to action learning, we describe the general framework of our algorithm, before detailing its architecture. In an experiment where a robot arm has to learn to use a flexible fishing line, we illustrate that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation and benefits from human demonstration properties to learn how to produce varied outcomes in the environment, while developing more precise control policies in large spaces.     

Experimental analysis of naïve Bayes classifier based on an attribute weighting framework with smooth kernel density estimations

Naïve Bayes learners are widely used, efficient, and effective supervised learning methods for labeled datasets in noisy environments. It has been shown that naïve Bayes learners produce reasonable performance compared with other machine learning algorithms. However, the conditional independence assumption of naïve Bayes learning imposes restrictions on the handling of real-world data. To relax the independence assumption, we propose a smooth kernel to augment weights for the likelihood estimation. We then select an attribute weighting method that uses the mutual information metric to cooperate with the proposed framework. A series of experiments are conducted on 17 UCI benchmark datasets to compare the accuracy of the proposed learner against that of other methods that employ a relaxed conditional independence assumption. The results demonstrate the effectiveness and efficiency of our proposed learning algorithm. The overall results also indicate the superiority of attribute-weighting methods over those that attempt to determine the structure of the network.     

Ensemble of naïve Bayesian approaches for the study of biofilm development in drinking water distribution systems

Various studies have been performed in relation to the influence that a number of characteristics of drinking water distribution systems (DWDSs) have on biofilm development. Nevertheless, their joint influence, apart from a few exceptions, has scarcely been studied due to the complexity of the community and the environment. In this paper, we apply various machine learning algorithms based on naïve Bayesian networks. Alternatives for the base naïve Bayesian model to outperform individual performances while maintaining simplicity are suggested. These alternatives include augmentation of the arcs in the graph, and initial bagging approaches. Finally, a combination of different naïve approaches in a bagging process that produces explanatory hybrid decision trees is proposed. As a result, it is possible to achieve a deeper understanding of the consequences that the interaction of the relevant hydraulic and physical factors of DWDSs has on biofilm development.     

Dynamics of opinion formation,social power evolution,and naïve learning in social networks

The past few decades have witnessed a prevalence of applying dynamical models to the study of social networks. This paper reviews recent advances in the investigation of social networks with a predominant focus on agent-based models. Starting from classical models of opinion dynamics, we survey several recently developed models on opinion formation and social power evolution. These models extend the classical models’ cognitive assumption that individuals’ opinions evolve on a single issue by incorporating various sociological or psychological hypotheses to account for the evolution of opinions over multiple or a sequence of interdependent issues. We summarize basic results on the asymptotic behaviors of these models and discuss their sociological interpretations. In addition, we show how these models play a role in the emergence of collective intelligence by applying them to a naïve learning setting. Novel results that reveal how individuals successfully learn an unknown truth over issue sequences are presented. Finally, we conclude the paper and discuss potential directions for future research.     

Active Learning for Vision-Based Robot Grasping

Reliable vision-based grasping has proved elusive outside of controlled environments. One approach towards building more flexible and domain-independent robot grasping systems is to employ learning to adapt the robot's perceptual and motor system to the task. However, one pitfall in robot perceptual and motor learning is that the cost of gathering the learning set may be unacceptably high. Active learning algorithms address this shortcoming by intelligently selecting actions so as to decrease the number of examples necessary to achieve good performance and also avoid separate training and execution phases, leading to higher autonomy. We describe the IE-ID3 algorithm, which extends the Interval Estimation (IE) active learning approach from discrete to real-valued learning domains by combining IE with a classification tree learning algorithm (ID-3). We present a robot system which rapidly learns to select the grasp approach directions using IE-ID3 given simplified superquadric shape approximations of objects. Initial results on a small set of objects show that a robot with a laser scanner system can rapidly learn to pick up new objects, and simulation studies show the superiority of the active learning approach for a simulated grasping task using larger sets of objects. Extensions of the approach and future areas of research incorporating more sophisticated perceptual and action representation are discussed     

Unravelling infectious disease eco-epidemiology using Bayesian networks and scenario analysis: A case study of leptospirosis in Fiji

Regression models are the standard approaches used in infectious disease epidemiology, but have limited ability to represent causality or complexity. We explore Bayesian networks (BNs) as an alternative approach for modelling infectious disease transmission, using leptospirosis as an example. Data were obtained from a leptospirosis study in Fiji in 2013. We compared the performance of naïve versus expert-structured BNs for modelling the relative importance of animal species in disease transmission in different ethnic groups and residential settings. For BNs of animal exposures at the individual/household level, R² for predicted versus observed infection rates were 0.59 for naïve and 0.75–0.93 for structured models of ethnic groups; and 0.54 for naïve and 0.93–1.00 for structured models of residential settings. BNs provide a promising approach for modelling infectious disease transmission under complex scenarios. The relative importance of animal species varied between subgroups, with important implications for more targeted public health control strategies.     

Motivation-Based Dependable Behavior Selection Using Probabilistic Affordance

Abstract

In this paper, we generate probabilistic affordances to select a dependable behavior based on motivation values. Dependable behavior, in our context, refers to behavior that is situation-adequate as well as goaloriented. The probabilistic affordance is designed as a multilayer naïve Bayesian classifier with respect to uncertainties and reusability. A multilayer naïve Bayesian classifier is a probabilistic model with multiple layers comprising conditional probability tables or probability distributions based on equivalence classes. The affordances consider situation-adequateness in given situations and suggest possibilities of behaviors based on Bayesian inference. In order to select a dependable behavior to achieve a task, the affordances are arranged based on a sequential structure. This is because accomplishing a task usually requires sequentially performed behaviors. Motivation values are generated using the arranged affordances and a motivation value propagation algorithm. A robot selects a dependable behavior based on these motivation values. To validate our proposed methods, we present experimental results of an entertainment robot called AIBO handling three tasks.     

HMM-Based Concept Learning for a Mobile Robot

We are developing an intelligent robot and attempting to teach it language. While there are many aspects of this research, for the purposes here the most important are the following ideas. Language is primarily based on semantics, not syntax, which is still the focus in speech recognition research these days. To truly learn meaning, a language engine cannot simply be a computer program running on a desktop computer analyzing speech. It must be part of a more general, embodied intelligent system, one capable of using associative learning to form concepts from the perception of experiences in the world, and further capable of manipulating those concepts symbolically. In this paper, we present a general cascade model for learning concepts, and explore the use of hidden Markov models (HMMs) as part of the cascade model. HMMs are capable of automatically learning and extracting the underlying structure of continuous-valued inputs and representing that structure in the states of the model. These states can then be treated as symbolic representations of the inputs. We show how a cascade of HMMs can be embedded in a small mobile robot and used to find correlations among sensory inputs to learn a set of symbolic concepts, which are used for decision making and could eventually be manipulated linguistically     

Learning accurate and concise naïve Bayes classifiers from attribute value taxonomies and data

In many application domains, there is a need for learning algorithms that can effectively exploit attribute value taxonomies (AVT)—hierarchical groupings of attribute values—to learn compact, comprehensible and accurate classifiers from data—including data that are partially specified. This paper describes AVT-NBL, a natural generalization of the naïve Bayes learner (NBL), for learning classifiers from AVT and data. Our experimental results show that AVT-NBL is able to generate classifiers that are substantially more compact and more accurate than those produced by NBL on a broad range of data sets with different percentages of partially specified values. We also show that AVT-NBL is more efficient in its use of training data: AVT-NBL produces classifiers that outperform those produced by NBL using substantially fewer training examples.     

Commanding a humanoid to move objects in a multimodal language

This article describes a study on a humanoid robot that moves objects at the request of its users. The robot understands commands in a multimodal language which combines spoken messages and two types of hand gesture. All of ten novice users directed the robot using gestures when they were asked to spontaneously direct the robot to move objects after learning the language for a short period of time. The success rate of multimodal commands was over 90%, and the users completed their tasks without trouble. They thought that gestures were preferable to, and as easy as, verbal phrases to inform the robot of action parameters such as direction, angle, step, width, and height. The results of the study show that the language is fairly easy for nonexperts to learn, and can be made more effective for directing humanoids to move objects by making the language more sophisticated and improving our gesture detector.     

Deep imitation learning for 3D navigation tasks

Deep learning techniques have shown success in learning from raw high-dimensional data in various applications. While deep reinforcement learning is recently gaining popularity as a method to train intelligent agents, utilizing deep learning in imitation learning has been scarcely explored. Imitation learning can be an efficient method to teach intelligent agents by providing a set of demonstrations to learn from. However, generalizing to situations that are not represented in the demonstrations can be challenging, especially in 3D environments. In this paper, we propose a deep imitation learning method to learn navigation tasks from demonstrations in a 3D environment. The supervised policy is refined using active learning in order to generalize to unseen situations. This approach is compared to two popular deep reinforcement learning techniques: deep-Q-networks and Asynchronous actor-critic (A3C). The proposed method as well as the reinforcement learning methods employ deep convolutional neural networks and learn directly from raw visual input. Methods for combining learning from demonstrations and experience are also investigated. This combination aims to join the generalization ability of learning by experience with the efficiency of learning by imitation. The proposed methods are evaluated on 4 navigation tasks in a 3D simulated environment. Navigation tasks are a typical problem that is relevant to many real applications. They pose the challenge of requiring demonstrations of long trajectories to reach the target and only providing delayed rewards (usually terminal) to the agent. The experiments show that the proposed method can successfully learn navigation tasks from raw visual input while learning from experience methods fail to learn an effective policy. Moreover, it is shown that active learning can significantly improve the performance of the initially learned policy using a small number of active samples.

     

Learning new uses of technology: Situational goal orientation matters

We study the decision to learn a new use of technology within a post-adoption context. This particular nuance of technology adoption is interesting because while the technology has been adopted at some level by both users and organizations, expanding technology use relies on users adopting additional tools and features within a given system on their own accord. This study addresses how situational goal orientation moderates the effects of ease of learning perceptions within the post-adoption context. We find that when a potential user has a situational learning goal orientation, they indicate intent to learn a new use of technology regardless of whether the technology is perceived to be easy or difficult to learn. However, potential users with a situational performance goal orientation indicate intent to learn the new system feature depending on ease of learning. These results have implications for future research using traditional technology acceptance parameters in the post-adoption context, and provide evidence that situational goal orientation is an effective managerial intervention for use in organizational training.     

Color learning and illumination invariance on mobile robots: A survey

Recent developments in sensor technology have made it feasible to use mobile robots in several fields, but robots still lack the ability to accurately sense the environment. A major challenge to the widespread deployment of mobile robots is the ability to function autonomously, learning useful models of environmental features, recognizing environmental changes, and adapting the learned models in response to such changes. This article focuses on such learning and adaptation in the context of color segmentation on mobile robots in the presence of illumination changes. The main contribution of this article is a survey of vision algorithms that are potentially applicable to color-based mobile robot vision. We therefore look at algorithms for color segmentation, color learning and illumination invariance on mobile robot platforms, including approaches that tackle just the underlying vision problems. Furthermore, we investigate how the inter-dependencies between these modules and high-level action planning can be exploited to achieve autonomous learning and adaptation. The goal is to determine the suitability of the state-of-the-art vision algorithms for mobile robot domains, and to identify the challenges that still need to be addressed to enable mobile robots to learn and adapt models for color, so as to operate autonomously in natural conditions.