REGAL : a regularization based algorithm for reinforcement learning in weakly communicating MDPs

We provide an algorithm that achieves the optimal regret rate in an unknown weakly communicating Markov Decision Process (MDP). The algorithm proceeds in episodes where, in each episode, it picks a policy using regularization based on the span of the optimal bias vector. For an MDP with S states and A actions whose optimal bias vector has span bounded by H, we show a regret bound of ~ O(HS p AT ). We also relate the span to various diameter-like quantities associated with the MDP, demonstrating how our results improve on previous regret bounds.

Current AI in games : a review

As the graphics race subsides and gamers grow weary of predictable and deterministic game characters, game developers must put aside their “old faithful” finite state machines and look to more advanced techniques that give the users the gaming experience they crave. The next industry breakthrough will be with characters that behave realistically and that can learn and adapt, rather than more polygons, higher resolution textures and more frames-per-second. This paper explores the various artificial intelligence techniques that are currently being used by game developers, as well as techniques that are new to the industry. The techniques covered in this paper are finite state machines, scripting, agents, flocking, fuzzy logic and fuzzy state machines decision trees, neural networks, genetic algorithms and extensible AI. This paper introduces each of these technique, explains how they can be applied to games and how commercial games are currently making use of them. Finally, the effectiveness of these techniques and their future role in the industry are evaluated.

Compressive sensing for gait recognition

Compressive Sensing (CS) is a popular signal processing technique, that can exactly reconstruct a signal given a small number of random projections of the original signal, provided that the signal is sufficiently sparse. We demonstrate the applicability of CS in the field of gait recognition as a very effective dimensionality reduction technique, using the gait energy image (GEI) as the feature extraction process. We compare the CS based approach to the principal component analysis (PCA) and show that the proposed method outperforms this baseline, particularly under situations where there are appearance changes in the subject. Applying CS to the gait features also avoids the need to train the models, by using a generalised random projection.

Does emotion modulate the blink reflex in human conditioning? Startle potentiation during pleasant and unpleasant cues in the picture-picture paradigm

Emotional processes modulate the size of the eyeblink startle reflex in a picture-viewing paradigm, but it is unclear whether emotional processes are responsible for blink modulation in human conditioning. Experiment 1 involved an aversive differential conditioning phase followed by an extinction phase in which acoustic startle probes were presented during CS+, CS-, and intertrial intervals. Valence ratings and affective priming showed the CS+ was unpleasant postacquisition. Blink startle magnitude was larger during CS+ than during CS-. Experiment 2 used the same design in two groups trained with pleasant or unpleasant pictorial USs. Ratings and affective priming indicated that the CS+ had become pleasant or unpleasant in the respective group. Regardless of CS valence, blink startle was larger during CS+ than CS- in both groups. Thus, startle was not modulated by CS valence.

Triangular Linguistic Fuzzy based performance measurement model for supply chain to assess leanness attributes

Increasing global competitiveness worldwide has forced manufacturing organizations to produce high-quality products more quickly and at a competitive cost. In order to reach these goals, they need good quality components from suppliers at optimum price and lead time. This actually forced all the companies to adapt different improvement practices such as lean manufacturing, Just in Time (JIT) and effective supply chain management. Applying new improvement techniques and tools cause higher establishment costs and more Information Delay (ID). On the contrary, these new techniques may reduce the risk of stock outs and affect supply chain flexibility to give a better overall performance. But industry people are unable to measure the overall affects of those improvement techniques with a standard evaluation model .So an effective overall supply chain performance evaluation model is essential for suppliers as well as manufacturers to assess their companies under different supply chain strategies. However, literature on lean supply chain performance evaluation is comparatively limited. Moreover, most of the models assumed random values for performance variables. The purpose of this paper is to propose an effective supply chain performance evaluation model using triangular linguistic fuzzy numbers and to recommend optimum ranges for performance variables for lean implementation. The model initially considers all the supply chain performance criteria (input, output and flexibility), converts the values to triangular linguistic fuzzy numbers and evaluates overall supply chain performance under different situations. Results show that with the proposed performance measurement model, improvement area for each variable can be accurately identified.

Catch up on passing off : what you need to know about this tricky tort

Advice for assisting clients on the law relating to passing off - elements of passing off - overlap with consumer protection and trade mark law - reputation - misrepresentation - damages and remedies

Affect, attention, or anticipatory arousal? Human blink startle modulation in forward and backward affective conditioning

Affect modulates the blink startle reflex in the picture-viewing paradigm, however, the process responsible for reflex modulation during conditional stimuli (CSs) that have acquired valence through affective conditioning remains unclear. In Experiment 1, neutral shapes (CSs) and valenced or neutral pictures (USs) were paired in a forward (CS → US) manner. Pleasantness ratings supported affective learning of positive and negative valence. Post-acquisition, blink reflexes were larger during the pleasant and unpleasant CSs than during the neutral CS. Rather than affect, attention or anticipatory arousal were suggested as sources of startle modulation. Experiment 2 confirmed that affective learning in the picture–picture paradigm was not affected by whether the CS preceded the US. Pleasantness ratings and affective priming revealed similar extents of affective learning following forward, backward or simultaneous pairings of CSs and USs. Experiment 3 utilized a backward conditioning procedure (US → CS) to minimize effects of US anticipation. Again, blink reflexes were larger during CSs paired with valenced USs regardless of US valence implicating attention rather than anticipatory arousal or affect as the process modulating startle in this paradigm.

Tensor query expansion : a cognitively motivated relevance model

In information retrieval, a user's query is often not a complete representation of their real information need. The user's information need is a cognitive construction, however the use of cognitive models to perform query expansion have had little study. In this paper, we present a cognitively motivated query expansion technique that uses semantic features for use in ad hoc retrieval. This model is evaluated against a state-of-the-art query expansion technique. The results show our approach provides significant improvements in retrieval effectiveness for the TREC data sets tested.

A taint marking approach to confidentiality violation detection

This article presents a novel approach to confidentiality violation detection based on taint marking. Information flows are dynamically tracked between applications and objects of the operating system such as files, processes and sockets. A confidentiality policy is defined by labelling sensitive information and defining which information may leave the local system through network exchanges. Furthermore, per application profiles can be defined to restrict the sets of information each application may access and/or send through the network. In previous works, we focused on the use of mandatory access control mechanisms for information flow tracking. In this current work, we have extended the previous information flow model to track network exchanges, and we are able to define a policy attached to network sockets. We show an example application of this extension in the context of a compromised web browser: our implementation detects a confidentiality violation when the browser attempts to leak private information to a remote host over the network.

Symbolic number : the integration of magnitude and spatial representations in children aged 6 to 8 years

The process of learning symbolic Arabic digits in early childhood requires that magnitude and spatial information integrates with the concept of symbolic digits. Previous research has separately investigated the development of automatic access to magnitude and spatial information from symbolic digits. However, developmental trajectories of symbolic number knowledge cannot be fully understood when considering components in isolation. In view of this, we have synthesized the existing lines of research and tested the use of both magnitude and spatial information with the same sample of British children in Years 1, 2 and 3 (6-8 years of age). The physical judgment task of the numerical Stroop paradigm (NSP) demonstrated that automatic access to magnitude was present from Year 1 and the distance effect signaled that a refined processing of numerical information had developed. Additionally, a parity judgment task showed that the onset of the Spatial-Numerical Association of Response Codes (SNARC) effect occurs in Year 2. These findings uncover the developmental timeline of how magnitude and spatial representations integrate with symbolic number knowledge during early learning of Arabic digits and resolve inconsistencies between previous developmental and experimental research lines.

An ontology-based mining approach for user search intent discovery

Discovering proper search intents is a vi- tal process to return desired results. It is constantly a hot research topic regarding information retrieval in recent years. Existing methods are mainly limited by utilizing context-based mining, query expansion, and user profiling techniques, which are still suffering from the issue of ambiguity in search queries. In this pa- per, we introduce a novel ontology-based approach in terms of a world knowledge base in order to construct personalized ontologies for identifying adequate con- cept levels for matching user search intents. An iter- ative mining algorithm is designed for evaluating po- tential intents level by level until meeting the best re- sult. The propose-to-attempt approach is evaluated in a large volume RCV1 data set, and experimental results indicate a distinct improvement on top precision after compared with baseline models.

Mobile applications of focused link discovery

Interaction with a mobile device remains difficult due to inherent physical limitations. This dif-ficulty is particularly evident for search, which re-quires typing. We extend the One-Search-Only search paradigm by adding a novel link-browsing scheme built on top of automatic link discovery. A prototype was built for iPhone and tested with 12 subjects. A post-use interview survey suggests that the extended paradigm improves the mobile information seeking experience.

Six degrees of cohesion in patent citation network

While the phrase “six degrees of separation” is widely used to characterize a variety of humanderived networks, in this study we show that in patent citation network, related patents are connected with an average distance of 6, whereas an average distance for a random pair of nodes in the graph is approximately 15. We use this information to improve the recall level in prior-art retrieval in the setting of blind relevance feedback without any textual knowledge.

Rule-based approach for identifying assertions in clinical free-text data

A rule-based approach for classifying previously identified medical concepts in the clinical free text into an assertion category is presented. There are six different categories of assertions for the task: Present, Absent, Possible, Conditional, Hypothetical and Not associated with the patient. The assertion classification algorithms were largely based on extending the popular NegEx and Context algorithms. In addition, a health based clinical terminology called SNOMED CT and other publicly available dictionaries were used to classify assertions, which did not fit the NegEx/Context model. The data for this task includes discharge summaries from Partners HealthCare and from Beth Israel Deaconess Medical Centre, as well as discharge summaries and progress notes from University of Pittsburgh Medical Centre. The set consists of 349 discharge reports, each with pairs of ground truth concept and assertion files for system development, and 477 reports for evaluation. The system’s performance on the evaluation data set was 0.83, 0.83 and 0.83 for recall, precision and F1-measure, respectively. Although the rule-based system shows promise, further improvements can be made by incorporating machine learning approaches.

Rare chicken rescue

Sound design for documentary is an under-researched field. The specific context of representation of emotional or mental states is particularly open to clichéd treatment. Such treatment in the media often ‘perpetuates inaccurate or negative assumptions about mental health issues in the wider community’ (Francis et al 2005: 11) by employing, for example, either jarring sound/music combinations to signify ‘madness’ or overtly saccharine music to educe sympathy. This project adopted a practice-based approach to discovering a considered aesthetic treatment designed to elicit a more empathetic audience response. A more discriminating engagement with the intentions of the film was cultivated by abandoning both the ‘representational naturalism’ and the ‘distilled, evocative realism’ of documentary sound design (Davies 2007: 18) in favour of a more lyrical or musical approach. To achieve this we manipulated perspective, tonal character and perceptions of space in the final mixing stage. The project was funded by the Film Australia National Interest Program, ABC TV and the Pacific Film and Television Commission. As a crucial contributor to the aesthetic of the project I was nominated in the funding application, and ultimately received an AFI Award for Best Sound in a Documentary in 2008. The film was honoured by The Film Critics Circle of Australia, The Slamdance Film Festival in Utah and The Sydney Film Festival. It has been favourably reviewed in national and international print media (The Age, Sydney Morning Herald, among others) as well as online film/culture zines and blogs.