Adaptive unsupervised learning of human actions

Automatic detection of suspicious activities in CCTV camera feeds is crucial to the success of video surveillance systems. Such a capability can help transform the dumb CCTV cameras into smart surveillance tools for fighting crime and terror. Learning and classification of basic human actions is a precursor to detecting suspicious activities. Most of the current approaches rely on a non-realistic assumption that a complete dataset of normal human actions is available. This paper presents a different approach to deal with the problem of understanding human actions in video when no prior information is available. This is achieved by working with an incomplete dataset of basic actions which are continuously updated. Initially, all video segments are represented by Bags-Of-Words (BOW) method using only Term Frequency-Inverse Document Frequency (TF-IDF) features. Then, a data-stream clustering algorithm is applied for updating the system's knowledge from the incoming video feeds. Finally, all the actions are classified into different sets. Experiments and comparisons are conducted on the well known Weizmann and KTH datasets to show the efficacy of the proposed approach.

Toward a fuzzy domain ontology extraction method for adaptive e-learning

With the widespread applications of electronic learning (e-Learning) technologies to education at all levels, increasing number of online educational resources and messages are generated from the corresponding e-Learning environments. Nevertheless, it is quite difficult, if not totally impossible, for instructors to read through and analyze the online messages to predict the progress of their students on the fly. The main contribution of this paper is the illustration of a novel concept map generation mechanism which is underpinned by a fuzzy domain ontology extraction algorithm. The proposed mechanism can automatically construct concept maps based on the messages posted to online discussion forums. By browsing the concept maps, instructors can quickly identify the progress of their students and adjust the pedagogical sequence on the fly. Our initial experimental results reveal that the accuracy and the quality of the automatically generated concept maps are promising. Our research work opens the door to the development and application of intelligent software tools to enhance e-Learning.

The link between age, career goals, and adaptive development for work-related learning among local government employees

More recently, lifespan development psychology models of adaptive development have been applied to the workforce to investigate ageing worker and lifespan issues. The current study uses the Learning and Development Survey (LDS) to investigate employee selection and engagement of learning and development goals and opportunities and constraints for learning at work in relation to demographics and career goals. It was found that mature age was associated with perceptions of preferential treatment of younger workers with respect to learning and development. Age was also correlated with several career goals. Findings suggest that younger workers’ learning and development options are better catered for in the workplace. Mature aged workers may compensate for unequal learning opportunities at work by studying for an educational qualification or seeking alternate job opportunities. The desire for a higher level job within the organization or educational qualification was linked to engagement in learning and development goals at work. It is suggested that an understanding of employee perceptions in the workplace in relation to goals and activities may be important in designing strategies to retain workers.

Margin-adaptive model selection in statistical learning

A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one to take into account that learning within a small model can be much easier than within a large one. Requiring this “strong margin adaptivity” makes the model selection problem more challenging. We first prove, in a general framework, that some penalization procedures (including local Rademacher complexities) exhibit this adaptivity when the models are nested. Contrary to previous results, this holds with penalties that only depend on the data. Our second main result is that strong margin adaptivity is not always possible when the models are not nested: for every model selection procedure (even a randomized one), there is a problem for which it does not demonstrate strong margin adaptivity.

Adaptive teachers embracing new ways of learning with robotics in Chinese schools

In July 2010, China announced the “National Plan for Medium and Long-term Education Reform and Development(2010-2020)” (PRC 2010). The Plan calls for an education system that: • promotes an integrated development which harnesses everyone’s talent; • combines learning and thinking; unifies knowledge and practice; • allows teachers to teach according to individuals’ needs; and • reforms education quality evaluation and personnel evaluation systems focusing on performance including character, knowledge, ability and other factors. This paper discusses the design and implementation of a Professional Learning Program (PLP) undertaken by 432 primary, middle and high school teachers in China. The aim of this initiative was to develop adaptive expertise in using technology that facilitated innovative science and technology teaching and learning as envisaged by the Chinese Ministry of Education’s (2010-2020) education reforms. Key principles derived from literature about professional learning and scaffolding of learning informed the design of the PLP. The analysis of data revealed that the participants had made substantial progress towards the development of adaptive expertise. This was manifested not only by advances in the participants’ repertoires of Subject Matter Knowledge and Pedagogical Content Knowledge but also in changes to their levels of confidence and identities as teachers. It was found that through time the participants had coalesced into a professional learning community that readily engaged in the sharing, peer review, reuse and adaption, and collaborative design of innovative science and technology learning and assessment activities.

Not learning from the past: Adaptive governance challenges for Australian natural resource management

Australia’s governance arrangements for NRM have evolved considerably over the last thirty years. The impact of changes in governance on NRM planning and delivery requires assessment. We undertake a multi-method program evaluation using adaptive governance principles as an analytical frame and apply this to Queensland to assess the impacts of governance change on NRM planning and governance outcomes. Data to inform our analysis includes: 1) a systematic review of sixteen audits/evaluations of Australian NRM over a fifteen-year period; 2) a review of Queensland’s first generation NRM Plans; and 3) outputs from a Queensland workshop on NRM planning. NRM has progressed from a bottom-up grassroots movement into a collaborative regional NRM model that has been centralised by the Australian Government. We found that while some adaptive governance challenges have been addressed, others remained unresolved. Results show that collaboration and elements of multi-level governance under the regional model were positive moves, but also that NRM arrangements contained structural deficiencies across multiple governance levels in relation to public involvement in decision-making and knowledge production for problem responsiveness. These problems for adaptive governance have been exacerbated since 2008. We conclude that the adaptive governance framework for NRM needs urgent attention so that important environmental management problems can be addressed.

An Adaptive Scheme for Learning the Probability Threshold in Pattern Recognition

The statistical minimum risk pattern recognition problem, when the classification costs are random variables of unknown statistics, is considered. Using medical diagnosis as a possible application, the problem of learning the optimal decision scheme is studied for a two-class twoaction case, as a first step. This reduces to the problem of learning the optimum threshold (for taking appropriate action) on the a posteriori probability of one class. A recursive procedure for updating an estimate of the threshold is proposed. The estimation procedure does not require the knowledge of actual class labels of the sample patterns in the design set. The adaptive scheme of using the present threshold estimate for taking action on the next sample is shown to converge, in probability, to the optimum. The results of a computer simulation study of three learning schemes demonstrate the theoretically predictable salient features of the adaptive scheme.

Reinforcement learning with average cost for adaptive control of traffic lights at intersections

We propose for the first time two reinforcement learning algorithms with function approximation for average cost adaptive control of traffic lights. One of these algorithms is a version of Q-learning with function approximation while the other is a policy gradient actor-critic algorithm that incorporates multi-timescale stochastic approximation. We show performance comparisons on various network settings of these algorithms with a range of fixed timing algorithms, as well as a Q-learning algorithm with full state representation that we also implement. We observe that whereas (as expected) on a two-junction corridor, the full state representation algorithm shows the best results, this algorithm is not implementable on larger road networks. The algorithm PG-AC-TLC that we propose is seen to show the best overall performance.

Adaptive Sleep-Wake Control using Reinforcement Learning in Sensor Networks

The aim in this paper is to allocate the `sleep time' of the individual sensors in an intrusion detection application so that the energy consumption from the sensors is reduced, while keeping the tracking error to a minimum. We propose two novel reinforcement learning (RL) based algorithms that attempt to minimize a certain long-run average cost objective. Both our algorithms incorporate feature-based representations to handle the curse of dimensionality associated with the underlying partially-observable Markov decision process (POMDP). Further, the feature selection scheme used in our algorithms intelligently manages the energy cost and tracking cost factors, which in turn assists the search for the optimal sleeping policy. We also extend these algorithms to a setting where the intruder's mobility model is not known by incorporating a stochastic iterative scheme for estimating the mobility model. The simulation results on a synthetic 2-d network setting are encouraging.

Various algorithms for optimization and learning in adaptive systems

This thesis discusses various methods for learning and optimization in adaptive systems. Overall, it emphasizes the relationship between optimization, learning, and adaptive systems; and it illustrates the influence of underlying hardware upon the construction of efficient algorithms for learning and optimization. Chapter 1 provides a summary and an overview.

Chapter 2 discusses a method for using feed-forward neural networks to filter the noise out of noise-corrupted signals. The networks use back-propagation learning, but they use it in a way that qualifies as unsupervised learning. The networks adapt based only on the raw input data-there are no external teachers providing information on correct operation during training. The chapter contains an analysis of the learning and develops a simple expression that, based only on the geometry of the network, predicts performance.

Chapter 3 explains a simple model of the piriform cortex, an area in the brain involved in the processing of olfactory information. The model was used to explore the possible effect of acetylcholine on learning and on odor classification. According to the model, the piriform cortex can classify odors better when acetylcholine is present during learning but not present during recall. This is interesting since it suggests that learning and recall might be separate neurochemical modes (corresponding to whether or not acetylcholine is present). When acetylcholine is turned off at all times, even during learning, the model exhibits behavior somewhat similar to Alzheimer's disease, a disease associated with the degeneration of cells that distribute acetylcholine.

Chapters 4, 5, and 6 discuss algorithms appropriate for adaptive systems implemented entirely in analog hardware. The algorithms inject noise into the systems and correlate the noise with the outputs of the systems. This allows them to estimate gradients and to implement noisy versions of gradient descent, without having to calculate gradients explicitly. The methods require only noise generators, adders, multipliers, integrators, and differentiators; and the number of devices needed scales linearly with the number of adjustable parameters in the adaptive systems. With the exception of one global signal, the algorithms require only local information exchange.

Adaptive capacity and learning to learn as leverage for social-ecological resilience

Ioan Fazey, John A. Fazey, Joern Fischer, Kate Sherren, John Warren, Reed F. Noss, Stephen R. Dovers (2007) Adaptive capacity and learning to learn as leverage for social?ecological resilience. Frontiers in Ecology and the Environment 5(7),375-380. RAE2008

Cerebellar Learning in an Opponent Motor Controller for Adaptive Load Compensation and Synergy Formation

This paper shows how a minimal neural network model of the cerebellum may be embedded within a sensory-neuro-muscular control system that mimics known anatomy and physiology. With this embedding, cerebellar learning promotes load compensation while also allowing both coactivation and reciprocal inhibition of sets of antagonist muscles. In particular, we show how synaptic long term depression guided by feedback from muscle stretch receptors can lead to trans-cerebellar gain changes that are load-compensating. It is argued that the same processes help to adaptively discover multi-joint synergies. Simulations of rapid single joint rotations under load illustrates design feasibility and stability.