On learning context-free and context-sensitive languages

The long short-term memory (LSTM) is not the only neural network which learns a context sensitive language. Second-order sequential cascaded networks (SCNs) are able to induce means from a finite fragment of a context-sensitive language for processing strings outside the training set. The dynamical behavior of the SCN is qualitatively distinct from that observed in LSTM networks. Differences in performance and dynamics are discussed.

An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization

Objective: Inpatient length of stay (LOS) is an important measure of hospital activity, health care resource consumption, and patient acuity. This research work aims at developing an incremental expectation maximization (EM) based learning approach on mixture of experts (ME) system for on-line prediction of LOS. The use of a batchmode learning process in most existing artificial neural networks to predict LOS is unrealistic, as the data become available over time and their pattern change dynamically. In contrast, an on-line process is capable of providing an output whenever a new datum becomes available. This on-the-spot information is therefore more useful and practical for making decisions, especially when one deals with a tremendous amount of data. Methods and material: The proposed approach is illustrated using a real example of gastroenteritis LOS data. The data set was extracted from a retrospective cohort study on all infants born in 1995-1997 and their subsequent admissions for gastroenteritis. The total number of admissions in this data set was n = 692. Linked hospitalization records of the cohort were retrieved retrospectively to derive the outcome measure, patient demographics, and associated co-morbidities information. A comparative study of the incremental learning and the batch-mode learning algorithms is considered. The performances of the learning algorithms are compared based on the mean absolute difference (MAD) between the predictions and the actual LOS, and the proportion of predictions with MAD < 1 day (Prop(MAD < 1)). The significance of the comparison is assessed through a regression analysis. Results: The incremental learning algorithm provides better on-line prediction of LOS when the system has gained sufficient training from more examples (MAD = 1.77 days and Prop(MAD < 1) = 54.3%), compared to that using the batch-mode learning. The regression analysis indicates a significant decrease of MAD (p-value = 0.063) and a significant (p-value = 0.044) increase of Prop(MAD

Interactive email filtering: Learning from misclassified examples

Learning from mistakes has proven to be an effective way of learning in the interactive document classifications. In this paper we propose an approach to effectively learning from mistakes in the email filtering process. Our system has employed both SVM and Winnow machine learning algorithms to learn from misclassified email documents and refine the email filtering process accordingly. Our experiments have shown that the training of an email filter becomes much effective and faster

Learning to play Pac-Man: An evolutionary, rule-based approach

Pac-Man is a well-known, real-time computer game that provides an interesting platform for research. We describe an initial approach to developing an artificial agent that replaces the human to play a simplified version of Pac-Man. The agent is specified as a simple finite state machine and ruleset. with parameters that control the probability of movement by the agent given the constraints of the maze at some instant of time. In contrast to previous approaches, the agent represents a dynamic strategy for playing Pac-Man, rather than a pre-programmed maze-solving method. The agent adaptively "learns" through the application of population-based incremental learning (PBIL) to adjust the agents' parameters. Experimental results are presented that give insight into some of the complexities of the game, as well as highlighting the limitations and difficulties of the representation of the agent.

Learning for fun: The unique contribution of educational leisure experiences

What do visitors want or expect from an educational leisure activity such as a visit to a museum, zoo, aquarium or other such experience? Is it to learn something or to experience learning? This paper uses the term 'learning for fun' to refer to the phenomenon in which visitors engage in a learning experience because they value and enjoy the process of learning itself. Five propositions regarding the nature of learning for fun are discussed, drawing on quantitative and qualitative data from visitors to a range of educational leisure activities. The commonalities between learning for fun and other theoretical constructs such as 'experience,' 'flow', 'intrinsic motivation', and 'curiosity' are explored. It is concluded that learning for fun is a unique and distinctive offering of educational leisure experiences, with implications for future research and experience design.

Parameter setting and statistical learning

Three main models of parameter setting have been proposed: the Variational model proposed by Yang (2002; 2004), the Structured Acquisition model endorsed by Baker (2001; 2005), and the Very Early Parameter Setting (VEPS) model advanced by Wexler (1998). The VEPS model contends that parameters are set early. The Variational model supposes that children employ statistical learning mechanisms to decide among competing parameter values, so this model anticipates delays in parameter setting when critical input is sparse, and gradual setting of parameters. On the Structured Acquisition model, delays occur because parameters form a hierarchy, with higher-level parameters set before lower-level parameters. Assuming that children freely choose the initial value, children sometimes will miss-set parameters. However when that happens, the input is expected to trigger a precipitous rise in one parameter value and a corresponding decline in the other value. We will point to the kind of child language data that is needed in order to adjudicate among these competing models.

Mummy! Ball! Fish!: Why English-learning children produce nouns earlier than verbs

When English-learning children begin using words the majority of their early utterances (around 80%) are nouns. Compared to nouns, there is a paucity of verbs or non-verb relational words, such as 'up' meaning 'pick me up'. The primary explanations to account for these differences in use either argue in support of a 'cognitive account', which claims that verbs entail more cognitive complexity than nouns, or they provide evidence challenging this account. In this paper I propose an additional explanation for children's noun/verb asymmetry. Presenting a 'multi-modal account' of word-learning based on children's gesture and word combinations, I show that at the one-word stage English-learning children use gestures to express verb-like elements which leaves their words free to express noun-like elements.

Fundamental Skills in Physics: Embedded Learning

Student attitudes towards a subject affect their learning. For students in physics service courses, relevance is emphasised by vocational applications. A similar strategy is being used for students who aspire to continued study of physics, in an introduction to fundamental skills in experimental physics – the concepts, computational tools and practical skills involved in appropriately obtaining and interpreting measurement data. An educational module is being developed that aims to enhance the student experience by embedding learning of these skills in the practicing physicist’s activity of doing an experiment (gravity estimation using a rolling pendulum). The group concentrates on particular skills prompted by challenges such as: • How can we get an answer to our question? • How good is our answer? • How can it be improved? This explicitly provides students the opportunity to consider and construct their own ideas. It gives them time to discuss, digest and practise without undue stress, thereby assisting them to internalise core skills. Design of the learning activity is approached in an iterative manner, via theoretical and practical considerations, with input from a range of teaching staff, and subject to trials of prototypes.

Demotivation: Understanding Resistance to English Language Learning - The Case of Vietnamese Students

Demotivation in English language learning was investigated, using Vietnam as a case study, with three main foci: (i) the reasons (i.e., the demotives) underlying demotivation; (ii) the degree of influence of different demotives; and (iii) students’ experiences in overcoming demotivation. Using stimulated recall essays from 100 university students of their foreign language learning experiences, the findings indicated that demotivation was a significant issue for EFL learning, and a framework for discussing the different sources of demotives was developed. While some categories of demotives occurred more frequent than others, no category appeared to be more or less difficult to overcome. Rather, students’ awareness of the role of English language and their determination to succeed were critical factors in overcoming demotivation.

Extending teaching and learning initiatives in the cross-disciplinary field of biotechnology

Our AUTC Biotechnology study (Phases 1 and 2) identified a range of areas that could benefit from a common approach by universities nationally. A national network of biotechnology educators needs to be solidified through more regular communication, biennial meetings, and development of methods for sharing effective teaching practices and industry placement strategies, for example. Our aims in this proposed study are to: a. Revisit the state of undergraduate biotechnology degree programs nationally to determine their rate of change in content, growth or shrinkage in student numbers (as the biotech industry has had its ups and downs in recent years), and sustainability within their institutions in light of career movements of key personnel, tightening budgets, and governmental funding priorities. b. Explore the feasibility of a range of initiatives to benefit university biotechnology education to determine factors such as how practical each one is, how much buy-in could be gained from potentially participating universities and industry counterparts, and how sustainable such efforts are. One of many such initiatives arising in our AUTC Biotech study was a national register of industry placements for final-year students. c. During scoping and feasibility study, to involve our colleagues who are teaching in biotechnology – and contributing disciplines. Their involvement is meant to yield not only meaningful insight into how to strengthen biotechnology teaching and learning but also to generate ‘buy-in’ on any initiatives that result from this effort.