The availability of on-line corpora is rapidly changing the field of natural language processing (NLP) from one dominated by theoretical models of often very specific linguistic phenomena to one guided by computational models that simultaneously account for a wide variety of phenomena that occur in real-world text. Thus far, among the best-performing and most robust systems for reading and summarizing large amounts of real-world text are knowledge-based natural language systems. These systems rely heavily on domain-specific, handcrafted knowledge to handle the myriad syntactic, semantic, and pragmatic ambiguities that pervade virtually all aspects of sentence analysis. Not surprisingly, however, generating this knowledge for new domains is time-consuming, difficult, and error-prone, and requires the expertise of computational linguists familiar with the underlying NLP system. This thesis presents Kenmore, a general framework for domain-specific knowledge acquisition for conceptual sentence analysis. To ease the acquisition of knowledge in new domains, Kenmore exploits an on-line corpus using symbolic machine learning techniques and robust sentence analysis while requiring only minimal human intervention. Unlike most approaches to knowledge acquisition for natural language systems, the framework uniformly addresses a range of subproblems in sentence analysis, each of which traditionally had required a separate computational mechanism. The thesis presents the results of using Kenmore with corpora from two real-world domains (1) to perform part-of-speech tagging, semantic feature tagging, and concept tagging of all open-class words in the corpus; (2) to acquire heuristics for part-of-speech disambiguation, semantic feature disambiguation, and concept activation; and (3) to find the antecedents of relative pronouns.

Thesis (Ph.D.)--Brown University, 2008. / Vita. Advisor: Michael J. Black. Includes bibliographical references (leaves 217-235).

Title page, contents and abstract only. The complete thesis in print form is available from the University of Adelaide Library. / "This thesis investigates how a digital training environment might be contructed to allow humans to study the emergent tactical methods of game-playing artificial systems in an effort to gain new tactical skill. After a theroy-based examination of such typically disparate fields as artificial life, computer animation and educative theory, this thesis suggests that learners might be able to acquire new tactical skills as required by observing suitable artifical intelligences via an interactive environment constructed in accordance with the principles of the non language-based educative methodology of ’reflective learning’." --p. vi. / http://proxy.library.adelaide.edu.au/login?url= http://library.adelaide.edu.au/cgi-bin/Pwebrecon.cgi?BBID=1278824 / Thesis (Ph.D.) -- University of Adelaide, School of Architecture, 2007

Title page, contents and abstract only. The complete thesis in print form is available from the University of Adelaide Library. / "This thesis investigates how a digital training environment might be contructed to allow humans to study the emergent tactical methods of game-playing artificial systems in an effort to gain new tactical skill. After a theroy-based examination of such typically disparate fields as artificial life, computer animation and educative theory, this thesis suggests that learners might be able to acquire new tactical skills as required by observing suitable artifical intelligences via an interactive environment constructed in accordance with the principles of the non language-based educative methodology of ’reflective learning’." --p. vi. / http://proxy.library.adelaide.edu.au/login?url= http://library.adelaide.edu.au/cgi-bin/Pwebrecon.cgi?BBID=1278824 / Thesis (Ph.D.) -- University of Adelaide, School of Architecture, 2007

abstract: As robotic technology and its various uses grow steadily more complex and ubiquitous, humans are coming into increasing contact with robotic agents. A large portion of such contact is cooperative interaction, where both humans and robots are required to work on the same application towards achieving common goals. These application scenarios are characterized by a need to leverage the strengths of each agent as part of a unified team to reach those common goals. To ensure that the robotic agent is truly a contributing team-member, it must exhibit some degree of autonomy in achieving goals that have been delegated to it. Indeed, a significant portion of the utility of such human-robot teams derives from the delegation of goals to the robot, and autonomy on the part of the robot in achieving those goals. In order to be considered truly autonomous, the robot must be able to make its own plans to achieve the goals assigned to it, with only minimal direction and assistance from the human. Automated planning provides the solution to this problem -- indeed, one of the main motivations that underpinned the beginnings of the field of automated planning was to provide planning support for Shakey the robot with the STRIPS system. For long, however, automated planners suffered from scalability issues that precluded their application to real world, real time robotic systems. Recent decades have seen a gradual abeyance of those issues, and fast planning systems are now the norm rather than the exception. However, some of these advances in speedup and scalability have been achieved by ignoring or abstracting out challenges that real world integrated robotic systems must confront. In this work, the problem of planning for human-hobot teaming is introduced. The central idea -- the use of automated planning systems as mediators in such human-robot teaming scenarios -- and the main challenges inspired from real world scenarios that must be addressed in order to make such planning seamless are presented: (i) Goals which can be specified or changed at execution time, after the planning process has completed; (ii) Worlds and scenarios where the state changes dynamically while a previous plan is executing; (iii) Models that are incomplete and can be changed during execution; and (iv) Information about the human agent's plan and intentions that can be used for coordination. These challenges are compounded by the fact that the human-robot team must execute in an open world, rife with dynamic events and other agents; and in a manner that encourages the exchange of information between the human and the robot. As an answer to these challenges, implemented solutions and a fielded prototype that combines all of those solutions into one planning system are discussed. Results from running this prototype in real world scenarios are presented, and extensions to some of the solutions are offered as appropriate. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2014

abstract: Reinforcement learning (RL) is a powerful methodology for teaching autonomous agents complex behaviors and skills. A critical component in most RL algorithms is the reward function -- a mathematical function that provides numerical estimates for desirable and undesirable states. Typically, the reward function must be hand-designed by a human expert and, as a result, the scope of a robot's autonomy and ability to safely explore and learn in new and unforeseen environments is constrained by the specifics of the designed reward function. In this thesis, I design and implement a stateful collision anticipation model with powerful predictive capability based upon my research of sequential data modeling and modern recurrent neural networks. I also develop deep reinforcement learning methods whose rewards are generated by self-supervised training and intrinsic signals. The main objective is to work towards the development of resilient robots that can learn to anticipate and avoid damaging interactions by combining visual and proprioceptive cues from internal sensors. The introduced solutions are inspired by pain pathways in humans and animals, because such pathways are known to guide decision-making processes and promote self-preservation. A new "robot dodge ball' benchmark is introduced in order to test the validity of the developed algorithms in dynamic environments. / Dissertation/Thesis / Masters Thesis Computer Science 2018

The self-organized nest construction behaviors of European paper wasps (Polistes dominula) show potential for adoption in artificial intelligence and robotic systems where centralized control proves challenging. However, P. dominula nest construction mechanisms are not fully understood. The goal of this research was to investigate how P. dominula nest structures stimulate worker actions. Simulation utilities were constructed in C++, C#, and Python. Two models from previous work, a three-dimensional model with weighted actions and a two-dimensional model with simple rule-based actions, were combined in a three-dimensional model with simple rules. Nest construction was simulated with a random selection rule, an age-based rule, a height requirement rule, and a height difference rule. Real and idealized nest data were used to evaluate simulated nests. Structures generated with age- and height-based rules showed more correlation with real and idealized nest structures than randomly-generated structures.

Background: As the landscape of the fashion industry is challenged by the emergence of big data and high sustainability demands, efficient solutions for product innovation and development are required. Artificial Intelligence (AI) is generating organizational shifts in various industries, but the fashion industry is still very early in its adoption. AI shows abilities to facilitate the challenges of the industry, and its application in creative design and product development processes is estimated to hold potential. Problem: As the fashion industry is characterized by creativity and human ideation, there is a need to evaluate if AI is compatible with the values of the industry. Management’s attitudes are proven to influence the adoption of digital technologies, leaving implications to study the attitudes of professionals in design and product development towards AI as well. Further, it is relevant to understand the possibilities and limitations of utilizing generative AI in creative processes, to ensure a successful implementation. Purpose: This thesis aims to investigate the implementation of AI in creative ideation and product development within the fashion industry, particularly exploring the attitudes of fashion professionals toward the relationship between human ideation and AI to determine the industry’s current position. Method: This study utilized qualitative research design by conducting 10 semi-structured interviews with professionals working in the fields of fashion design, product development, and AI. Conclusion: The results show that AI is currently not implemented within fashion, among the interviewees. The study identified determinants, such as awareness, attitudes, data, knowledge, objectives, and competencies that influence the adoption of AI, in the early stages. The attitudes toward AI are an essential factor in the early stages of adoption.

Comic books are a unique and increasingly popular form of entertainment combining visual and textual elements of communication. This work pertains to making comic books more accessible. Specifically, this paper explains how we detect elements such as speech bubbles present in Japanese comic book panels. Some applications of the work presented in this paper are automatic detection of text and its transformation into audio or into other languages. Automatic detection of elements can also allow reasoning and analysis at a deeper semantic level than what’s possible today. Our approach uses an expert system and a machine learning system. The expert system process information from images and inspires feature sets which help train the machine learning system. The expert system detects speech bubbles based on heuristics. The machine learning system uses machine learning algorithms. Specifically, Naive Bayes, Maximum Entropy, and support vector machine are used to detect speech bubbles. The algorithms are trained in a fully-supervised way and a semi-supervised way. Both the expert system and the machine learning system achieved high accuracy. We are able to train the machine learning algorithms to detect speech bubbles just as accurately as the expert system. We also applied the same approach to eye detection of characters in the panels, and are able to detect majority of the eyes but with low precision. However, we are able to improve the performance of our eye detection system significantly by combining the SVM and either the Naive Bayes or the AdaBoost classifiers.

No description available.