Personalization in tag ontology learning for recommendation making

Due to the explosive growth of the Web, the domain of Web personalization has gained great momentum both in the research and commercial areas. One of the most popular web personalization systems is recommender systems. In recommender systems choosing user information that can be used to profile users is very crucial for user profiling. In Web 2.0, one facility that can help users organize Web resources of their interest is user tagging systems. Exploring user tagging behavior provides a promising way for understanding users’ information needs since tags are given directly by users. However, free and relatively uncontrolled vocabulary makes the user self-defined tags lack of standardization and semantic ambiguity. Also, the relationships among tags need to be explored since there are rich relationships among tags which could provide valuable information for us to better understand users. In this paper, we propose a novel approach for learning tag ontology based on the widely used lexical database WordNet for capturing the semantics and the structural relationships of tags. We present personalization strategies to disambiguate the semantics of tags by combining the opinion of WordNet lexicographers and users’ tagging behavior together. To personalize further, clustering of users is performed to generate a more accurate ontology for a particular group of users. In order to evaluate the usefulness of the tag ontology, we use the tag ontology in a pilot tag recommendation experiment for improving the recommendation performance by exploiting the semantic information in the tag ontology. The initial result shows that the personalized information has improved the accuracy of the tag recommendation.

Intelligent tutoring system for learning PHP

This thesis investigates the possibility of using an adaptive tutoring system for beginning programming students. The work involved, designing, developing and evaluating such a system and showing that it was effective in increasing the students’ test scores. In doing so, Artificial Intelligence techniques were used to analyse PHP programs written by students and to provide feedback based on any specific errors made by them. Methods were also included to provide students with the next best exercise to suit their particular level of knowledge.

Near knowledge : inductive learning systems in law

Induction is an interesting model of legal reasoning, since it provides a method of capturing initial states of legal principles and rules, and adjusting these principles and rules over time as the law changes. In this article I explain how Artificial Intelligence-based inductive learning algorithms work, and show how they have been used in law to model legal domains. I identify some problems with implementations undertaken in law to date, and create a taxonomy of appropriate cases to use in legal inductive inferencing systems. I suggest that inductive learning algorithms have potential in modeling law, but that the artificial intelligence implementations to date are problematic. I argue that induction should be further investigated, since it has the potential to be an extremely useful mechanism for understanding legal domains.

Locally weighted learning methods for non-rigid robot control

This thesis develops a novel approach to robot control that learns to account for a robot's dynamic complexities while executing various control tasks using inspiration from biological sensorimotor control and machine learning. A robot that can learn its own control system can account for complex situations and adapt to changes in control conditions to maximise its performance and reliability in the real world. This research has developed two novel learning methods, with the aim of solving issues with learning control of non-rigid robots that incorporate additional dynamic complexities. The new learning control system was evaluated on a real three degree-of-freedom elastic joint robot arm with a number of experiments: initially validating the learning method and testing its ability to generalise to new tasks, then evaluating the system during a learning control task requiring continuous online model adaptation.

Do-Rank: DCG optimization for learning-to-rank in tag-based item recommendation systems

Discounted Cumulative Gain (DCG) is a well-known ranking evaluation measure for models built with multiple relevance graded data. By handling tagging data used in recommendation systems as an ordinal relevance set of {negative,null,positive}, we propose to build a DCG based recommendation model. We present an efficient and novel learning-to-rank method by optimizing DCG for a recommendation model using the tagging data interpretation scheme. Evaluating the proposed method on real-world datasets, we demonstrate that the method is scalable and outperforms the benchmarking methods by generating a quality top-N item recommendation list.

Automating marine mammal detection in aerial images captured during wildlife surveys: A deep learning approach

Aerial surveys conducted using manned or unmanned aircraft with customized camera payloads can generate a large number of images. Manual review of these images to extract data is prohibitive in terms of time and financial resources, thus providing strong incentive to automate this process using computer vision systems. There are potential applications for these automated systems in areas such as surveillance and monitoring, precision agriculture, law enforcement, asset inspection, and wildlife assessment. In this paper, we present an efficient machine learning system for automating the detection of marine species in aerial imagery. The effectiveness of our approach can be credited to the combination of a well-suited region proposal method and the use of Deep Convolutional Neural Networks (DCNNs). In comparison to previous algorithms designed for the same purpose, we have been able to dramatically improve recall to more than 80% and improve precision to 27% by using DCNNs as the core approach.

Design optimisation using advanced artificial intelligent system coupled to hybrid-game strategies

One of the main aims in artificial intelligent system is to develop robust and efficient optimisation methods for Multi-Objective (MO) and Multidisciplinary Design (MDO) design problems. The paper investigates two different optimisation techniques for multi-objective design optimisation problems. The first optimisation method is a Non-Dominated Sorting Genetic Algorithm II (NSGA-II). The second method combines the concepts of Nash-equilibrium and Pareto optimality with Multi-Objective Evolutionary Algorithms (MOEAs) which is denoted as Hybrid-Game. Numerical results from the two approaches are compared in terms of the quality of model and computational expense. The benefit of using the distributed hybrid game methodology for multi-objective design problems is demonstrated.

Discovering, applying and integrating self-knowledge : a grounded theory study of learning in life coaching

Professional coaching is a rapidly expanding field with interdisciplinary roots and broad application. However, despite abundant prescriptive literature, research into the process of coaching, and especially life coaching, is minimal. Similarly, although learning is inherently recognised in the process of coaching, and coaching is increasingly being recognised as a means of enhancing teaching and learning, the process of learning in coaching is little understood, and learning theory makes up only a small part of the evidence-based coaching literature. In this grounded theory study of life coaches and their clients, the process of learning in life coaching across a range of coaching models is examined and explained. The findings demonstrate how learning in life coaching emerged as a process of discovering, applying and integrating self-knowledge, which culminated in the development of self. This process occurred through eight key coaching processes shared between coaches and clients and combined a multitude of learning theory.

Hybrid robot control and SLAM for persistent navigation and mapping

For a mobile robot to operate autonomously in real-world environments, it must have an effective control system and a navigation system capable of providing robust localization, path planning and path execution. In this paper we describe the work investigating synergies between mapping and control systems. We have integrated development of a control system for navigating mobile robots and a robot SLAM system. The control system is hybrid in nature and tightly coupled with the SLAM system; it uses a combination of high and low level deliberative and reactive control processes to perform obstacle avoidance, exploration, global navigation and recharging, and draws upon the map learning and localization capabilities of the SLAM system. The effectiveness of this hybrid, multi-level approach was evaluated in the context of a delivery robot scenario. Over a period of two weeks the robot performed 1143 delivery tasks to 11 different locations with only one delivery failure (from which it recovered), travelled a total distance of more than 40km, and recharged autonomously a total of 23 times. In this paper we describe the combined control and SLAM system and discuss insights gained from its successful application in a real-world context.

A Bayesian approach for place recognition

This paper presents a robust place recognition algorithm for mobile robots. The framework proposed combines nonlinear dimensionality reduction, nonlinear regression under noise, and variational Bayesian learning to create consistent probabilistic representations of places from images. These generative models are learnt from a few images and used for multi-class place recognition where classification is computed from a set of feature-vectors. Recognition can be performed in near real-time and accounts for complexity such as changes in illumination, occlusions and blurring. The algorithm was tested with a mobile robot in indoor and outdoor environments with sequences of 1579 and 3820 images respectively. This framework has several potential applications such as map building, autonomous navigation, search-rescue tasks and context recognition.

The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

Sample complexity results from computational learning theory, when applied to neural network learning for pattern classification problems, suggest that for good generalization performance the number of training examples should grow at least linearly with the number of adjustable parameters in the network. Results in this paper show that if a large neural network is used for a pattern classification problem and the learning algorithm finds a network with small weights that has small squared error on the training patterns, then the generalization performance depends on the size of the weights rather than the number of weights. For example, consider a two-layer feedforward network of sigmoid units, in which the sum of the magnitudes of the weights associated with each unit is bounded by A and the input dimension is n. We show that the misclassification probability is no more than a certain error estimate (that is related to squared error on the training set) plus A3 √((log n)/m) (ignoring log A and log m factors), where m is the number of training patterns. This may explain the generalization performance of neural networks, particularly when the number of training examples is considerably smaller than the number of weights. It also supports heuristics (such as weight decay and early stopping) that attempt to keep the weights small during training. The proof techniques appear to be useful for the analysis of other pattern classifiers: when the input domain is a totally bounded metric space, we use the same approach to give upper bounds on misclassification probability for classifiers with decision boundaries that are far from the training examples.

Model selection and error estimation

We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalization: any good error estimate may be converted into a data-based penalty function and the performance of the estimate is governed by the quality of the error estimate. We consider several penalty functions, involving error estimates on independent test data, empirical VC dimension, empirical VC entropy, and margin-based quantities. We also consider the maximal difference between the error on the first half of the training data and the second half, and the expected maximal discrepancy, a closely related capacity estimate that can be calculated by Monte Carlo integration. Maximal discrepancy penalty functions are appealing for pattern classification problems, since their computation is equivalent to empirical risk minimization over the training data with some labels flipped.

Infinite-horizon policy-gradient estimation

Gradient-based approaches to direct policy search in reinforcement learning have received much recent attention as a means to solve problems of partial observability and to avoid some of the problems associated with policy degradation in value-function methods. In this paper we introduce GPOMDP, a simulation-based algorithm for generating a biased estimate of the gradient of the average reward in Partially Observable Markov Decision Processes (POMDPs) controlled by parameterized stochastic policies. A similar algorithm was proposed by Kimura, Yamamura, and Kobayashi (1995). The algorithm's chief advantages are that it requires storage of only twice the number of policy parameters, uses one free parameter β ∈ [0,1) (which has a natural interpretation in terms of bias-variance trade-off), and requires no knowledge of the underlying state. We prove convergence of GPOMDP, and show how the correct choice of the parameter β is related to the mixing time of the controlled POMDP. We briefly describe extensions of GPOMDP to controlled Markov chains, continuous state, observation and control spaces, multiple-agents, higher-order derivatives, and a version for training stochastic policies with internal states. In a companion paper (Baxter, Bartlett, & Weaver, 2001) we show how the gradient estimates generated by GPOMDP can be used in both a traditional stochastic gradient algorithm and a conjugate-gradient procedure to find local optima of the average reward. ©2001 AI Access Foundation and Morgan Kaufmann Publishers. All rights reserved.

Rademacher and Gaussian complexities: Risk bounds and structural results

We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we prove general risk bounds in terms of these complexities. We consider function classes that can be expressed as combinations of functions from basis classes and show how the Rademacher and Gaussian complexities of such a function class can be bounded in terms of the complexity of the basis classes. We give examples of the application of these techniques in finding data-dependent risk bounds for decision trees, neural networks and support vector machines.