Number of options in a movement sequence affects learners' behavior in a self-controlled practice condition

Self controlling practice implies a process of decision making which suggests that the options in a self controlled practice condition could affect learners The number of task components with no fixed position in a movement sequence may affect the (Nay learners self control their practice A 200 cm coincident timing track with 90 light emitting diodes (LEDs)-the first and the last LEDs being the warning and the target lights respectively was set so that the apparent speed of the light along the track was 1 33 m/sec Participants were required to touch six sensors sequentially the last one coincidently with the lighting of the tar get light (timing task) Group 1 (n=55) had only one constraint and were instructed to touch the sensors in any order except for the last sensor which had to be the one positioned close to the target light Group 2 (n=53) had three constraints the first two and the last sensor to be touched Both groups practiced the task until timing error was less than 30 msec on three consecutive trials There were no statistically significant differences between groups in the number of trials needed to reach the performance criterion but (a) participants in Group 2 created fewer sequences corn pared to Group 1 and (b) were more likely to use the same sequence throughout the learning process The number of options for a movement sequence affected the way learners self-controlled their practice but had no effect on the amount of practice to reach criterion performance.

Learning the dynamics of embedded clauses

Recent work by Siegelmann has shown that the computational power of recurrent neural networks matches that of Turing Machines. One important implication is that complex language classes (infinite languages with embedded clauses) can be represented in neural networks. Proofs are based on a fractal encoding of states to simulate the memory and operations of stacks. In the present work, it is shown that similar stack-like dynamics can be learned in recurrent neural networks from simple sequence prediction tasks. Two main types of network solutions are found and described qualitatively as dynamical systems: damped oscillation and entangled spiraling around fixed points. The potential and limitations of each solution type are established in terms of generalization on two different context-free languages. Both solution types constitute novel stack implementations - generally in line with Siegelmann's theoretical work - which supply insights into how embedded structures of languages can be handled in analog hardware.

A didactic sequence of elementary geometric optics Informed by history and philosophy of science

The concepts and instruments required for the teaching and learning of geometric optics are introduced in the didactic processwithout a proper didactic transposition. This claim is secured by the ample evidence of both wide- and deep-rooted alternative concepts on the topic. Didactic transposition is a theory that comes from a reflection on the teaching and learning process in mathematics but has been used in other disciplinary fields. It will be used in this work in order to clear up the main obstacles in the teachinglearning process of geometric optics. We proceed to argue that since Newton’s approach to optics, in his Book I of Opticks, is independent of the corpuscular or undulatory nature of light, it is the most suitable for a constructivist learning environment. However, Newton’s theory must be subject to a proper didactic transposition to help overcome the referred alternative concepts. Then is described our didactic transposition in order to create knowledge to be taught using a dialogical process between students’ previous knowledge, history of optics and the desired outcomes on geometrical optics in an elementary pre-service teacher training course. Finally, we use the scheme-facet structure of knowledge both to analyse and discuss our results as well as to illuminate shortcomings that must be addressed in our next stage of the inquiry.

Learning joint representations for order and timing of perceptual-motor sequences: a dynamic neural field approach

Many of our everyday tasks require the control of the serial order and the timing of component actions. Using the dynamic neural field (DNF) framework, we address the learning of representations that support the performance of precisely time action sequences. In continuation of previous modeling work and robotics implementations, we ask specifically the question how feedback about executed actions might be used by the learning system to fine tune a joint memory representation of the ordinal and the temporal structure which has been initially acquired by observation. The perceptual memory is represented by a self-stabilized, multi-bump activity pattern of neurons encoding instances of a sensory event (e.g., color, position or pitch) which guides sequence learning. The strength of the population representation of each event is a function of elapsed time since sequence onset. We propose and test in simulations a simple learning rule that detects a mismatch between the expected and realized timing of events and adapts the activation strengths in order to compensate for the movement time needed to achieve the desired effect. The simulation results show that the effector-specific memory representation can be robustly recalled. We discuss the impact of the fast, activation-based learning that the DNF framework provides for robotics applications.

Learning-induced plasticity in human audition: Objects, time, and space.

The human auditory system is comprised of specialized but interacting anatomic and functional pathways encoding object, spatial, and temporal information. We review how learning-induced plasticity manifests along these pathways and to what extent there are common mechanisms subserving such plasticity. A first series of experiments establishes a temporal hierarchy along which sounds of objects are discriminated along basic to fine-grained categorical boundaries and learned representations. A widespread network of temporal and (pre)frontal brain regions contributes to object discrimination via recursive processing. Learning-induced plasticity typically manifested as repetition suppression within a common set of brain regions. A second series considered how the temporal sequence of sound sources is represented. We show that lateralized responsiveness during the initial encoding phase of pairs of auditory spatial stimuli is critical for their accurate ordered perception. Finally, we consider how spatial representations are formed and modified through training-induced learning. A population-based model of spatial processing is supported wherein temporal and parietal structures interact in the encoding of relative and absolute spatial information over the initial ∼300ms post-stimulus onset. Collectively, these data provide insights into the functional organization of human audition and open directions for new developments in targeted diagnostic and neurorehabilitation strategies.

Free-and open source software for a course on network management: authoring and enactment of scripts based on collaborative learning strategies

This paper describes a Computer-Supported Collaborative Learning (CSCL) case study in engineering education carried out within the context of a network management course. The case study shows that the use of two computing tools developed by the authors and based on Free- and Open-Source Software (FOSS) provide significant educational benefits over traditional engineering pedagogical approaches in terms of both concepts and engineering competencies acquisition. First, the Collage authoring tool guides and supports the course teacher in the process of authoring computer-interpretable representations (using the IMS Learning Design standard notation) of effective collaborative pedagogical designs. Besides, the Gridcole system supports the enactment of that design by guiding the students throughout the prescribed sequence of learning activities. The paper introduces the goals and context of the case study, elaborates onhow Collage and Gridcole were employed, describes the applied evaluation methodology, anddiscusses the most significant findings derived from the case study.

Strong minimax lower bounds for learning

Minimax lower bounds for concept learning state, for example, thatfor each sample size $n$ and learning rule $g_n$, there exists a distributionof the observation $X$ and a concept $C$ to be learnt such that the expectederror of $g_n$ is at least a constant times $V/n$, where $V$ is the VC dimensionof the concept class. However, these bounds do not tell anything about therate of decrease of the error for a {\sl fixed} distribution--concept pair.\\In this paper we investigate minimax lower bounds in such a--stronger--sense.We show that for several natural $k$--parameter concept classes, includingthe class of linear halfspaces, the class of balls, the class of polyhedrawith a certain number of faces, and a class of neural networks, for any{\sl sequence} of learning rules $\{g_n\}$, there exists a fixed distributionof $X$ and a fixed concept $C$ such that the expected error is larger thana constant times $k/n$ for {\sl infinitely many n}. We also obtain suchstrong minimax lower bounds for the tail distribution of the probabilityof error, which extend the corresponding minimax lower bounds.

Learning of courtship components in Drosophila mercatorum (Paterson & Wheller) (Diptera, Drosophilidae)

In Drosophila, courtship is an elaborate sequence of behavioural patterns that enables the flies to identify conspecific mates from those of closely related species. This is important because drosophilids usually gather in feeding sites, where males of various species court females vigorously. We investigated the effects of previous experience on D. mercatorum courtship, by testing if virgin males learn to improve their courtship by observing other flies (social learning), or by adjusting their pre-existent behaviour based on previous experiences (facilitation). Behaviours recorded in a controlled environment were courtship latency, courtship (orientation, tapping and wing vibration), mating and other behaviours not related to sexual activities. This study demonstrated that males of D. mercatorum were capable of improving their mating ability based on prior experiences, but they had no social learning on the development of courtship.

Intrahippocampal cholinergic grafts in aged rats compensate impairments in a radial maze and in a place learning task

Age-related cognitive impairments were studied in rats kept in semi-enriched conditions during their whole life, and tested during ontogeny and adult life in various classical spatial tasks. In addition, the effect of intrahippocampal grafts of fetal septal-diagonal band tissue, rich in cholinergic neurons, was studied in some of these subjects. The rats received bilateral cell suspensions when aged 23-24 months. Starting 4 weeks after grafting, they were trained during 5 weeks in an 8-arm maze made of connected plexiglass tunnels. No age-related impairment was detected during the first eight trials, when the maze shape was that of a classical radial maze in which the rats had already been trained when young. The older rats were impaired when the task was made more difficult by rendering two arms parallel to each other. They developed an important neglect of one of the parallel tunnels resulting in a high amount of errors before completion of the task. In addition, the old rats developed a systematic response pattern of visits to adjacent arms in a sequence, which was not observed in the younger subjects. None of these behaviours were observed in the old rats with a septal transplant. Sixteen weeks after grafting, another experiment was conducted in a homing hole board task. Rats were allowed to escape from a large circular arena through one hole out of many, and to reach home via a flexible tube under the table. The escape hole was at a fixed position according to distant room cues, and olfactory cues were made irrelevant by rotating the table between the trials. An additional cue was placed on the escape position. No age-related difference in escape was observed during training. During a probe trial with no hole connected and no proximal cue present, the old untreated rats were less clearly focussed on the training sector than were either the younger or the grafted old subjects. Taken together, these experiments indicate that enriched housing conditions and spatial training during adult life do not protect against all age-related deterioration in spatial ability. However, it might be that the considerable improvement observed in the grafted subjects results from an interaction between the graft treatment and the housing conditions.

Spatial learning by rats across visually disconnected environments

Two spatial tasks were designed to test specific properties of spatial representation in rats. In the first task, rats were trained to locate an escape hole at a fixed position in a visually homogeneous arena. This arena was connected with a periphery where a full view of the room environment existed. Therefore, rats were dependent on their memory trace of the previous position in the periphery to discriminate a position within the central region. Under these experimental conditions, the test animals showed a significant discrimination of the training position without a specific local view. In the second task, rats were trained in a radial maze consisting of tunnels that were transparent at their distal ends only. Because the central part of the maze was non-transparent, rats had to plan and execute appropriate trajectories without specific visual feedback from the environment. This situation was intended to encourage the reliance on prospective memory of the non-visited arms in selecting the following move. Our results show that acquisition performance was only slightly decreased compared to that shown in a completely transparent maze and considerably higher than in a translucent maze or in darkness. These two series of experiments indicate (1) that rats can learn about the relative position of different places with no common visual panorama, and (2) that they are able to plan and execute a sequence of visits to several places without direct visual feed-back about their relative position.

Long-lasting mnemotropic effect of substance P and its N-terminal fragment (SP1-7) on avoidance learning

We investigated the long-lasting effect of peripheral injection of the neuropeptide substance P (SP) and of some N- or C-terminal SP fragments (SPN and SPC, respectively) on retention test performance of avoidance learning. Male Wistar rats (220 to 280 g) were trained in an inhibitory step-down avoidance task and tested 24 h or 21 days later. Immediately after the training trial rats received an intraperitoneal injection of SP (50 µg/kg), SPN 1-7 (167 µg/kg) or SPC 7-11 (134 µg/kg). Control groups were injected with vehicle or SP 5 h after the training trial. The immediate post-training administration of SP and SPN, but not SPC, facilitated avoidance behavior in rats tested 24 h or 21 days later, i.e., the retention test latencies of the SP and SPN groups were significantly longer (P<0.05, Mann-Whitney U-test) during both training-test intervals. These observations suggest that the memory-enhancing effect of SP is long-lasting and that the amino acid sequence responsible for this effect is encoded by its N-terminal part

Sentence Compression with Supervised Machine Learning

The subject of the thesis is automatic sentence compression with machine learning, so that the compressed sentences remain both grammatical and retain their essential meaning. There are multiple possible uses for the compression of natural language sentences. In this thesis the focus is generation of television program subtitles, which often are compressed version of the original script of the program. The main part of the thesis consists of machine learning experiments for automatic sentence compression using different approaches to the problem. The machine learning methods used for this work are linear-chain conditional random fields and support vector machines. Also we take a look which automatic text analysis methods provide useful features for the task. The data used for machine learning is supplied by Lingsoft Inc. and consists of subtitles in both compressed an uncompressed form. The models are compared to a baseline system and comparisons are made both automatically and also using human evaluation, because of the potentially subjective nature of the output. The best result is achieved using a CRF - sequence classification using a rich feature set. All text analysis methods help classification and most useful method is morphological analysis. Tutkielman aihe on suomenkielisten lauseiden automaattinen tiivistäminen koneellisesti, niin että lyhennetyt lauseet säilyttävät olennaisen informaationsa ja pysyvät kieliopillisina. Luonnollisen kielen lauseiden tiivistämiselle on monta käyttötarkoitusta, mutta tässä tutkielmassa aihetta lähestytään television ohjelmien tekstittämisen kautta, johon käytännössä kuuluu alkuperäisen tekstin lyhentäminen televisioruudulle paremmin sopivaksi. Tutkielmassa kokeillaan erilaisia koneoppimismenetelmiä tekstin automaatiseen lyhentämiseen ja tarkastellaan miten hyvin erilaiset luonnollisen kielen analyysimenetelmät tuottavat informaatiota, joka auttaa näitä menetelmiä lyhentämään lauseita. Lisäksi tarkastellaan minkälainen lähestymistapa tuottaa parhaan lopputuloksen. Käytetyt koneoppimismenetelmät ovat tukivektorikone ja lineaarisen sekvenssin mallinen CRF. Koneoppimisen tukena käytetään tekstityksiä niiden eri käsittelyvaiheissa, jotka on saatu Lingsoft OY:ltä. Luotuja malleja vertaillaan Lopulta mallien lopputuloksia evaluoidaan automaattisesti ja koska teksti lopputuksena on jossain määrin subjektiivinen myös ihmisarviointiin perustuen. Vertailukohtana toimii kirjallisuudesta poimittu menetelmä. Tutkielman tuloksena paras lopputulos saadaan aikaan käyttäen CRF sekvenssi-luokittelijaa laajalla piirrejoukolla. Kaikki kokeillut teksin analyysimenetelmät auttavat luokittelussa, joista tärkeimmän panoksen antaa morfologinen analyysi.

Exploring the events that engage graduate students in transformative learning /

This research explored the events that engaged graduate students in transformative learning within a graduate program in education. This context was chosen because one objective of a graduate program is to facilitate critical thinking and transformative learning. The question ofhow adult learners perceive and experience learning steered the direction ofthis study. However, the purpose ofthis research was to study critical incidents that led to profound cognitive and affective changes as perceived by the graduate students. Specifically, the questions to be answered were what critical incidents happened to graduate students while in the Master ofEducation program, how were the incidents experienced, and what transformation resulted? The research design evolved over the course of a year and was highly influenced by previous empirical studies and criticisms oftransformative learning theory. The overall design was qualitative and phenomenological. A critical and interpretive approach was made to empirical data collected through a critical incident questionnaire and in-depth interviews. Inductive analysis allowed theory to be built from the data by making comparisons. New questions emerged and attention was given to social context, the passage oftime, and sequence ofevents in order to give meaning and translation ofthe participants' experiences and to build the interpretive narratives. Deductive analysis was also used on the data and a blending ofthe two forms of analysis; this resulted in the development ofa foundational model for transformative learning to be built.The data revealed critical incidents outside ofthe graduate school program that occurred in childhood or adult life prior to graduate school. Since context of individuals' lives had been an important critique of past transformative learning models and studies, this research expanded the original boundaries of this study beyond graduate school to incorporate incidents that occurred outside of graduate school. Critical incidents were categorized into time-related, people-related, and circumstancerelated themes. It was clear that participants were influenced and molded by the stage oftheir life, personal experiences, familial and cultural conditioning, and even historic events. The model developed in this document fiom an overview ofthe fmdings identifies a four-stage process of life difficulty, disintegration, reintegration, and completion that all participants' followed. The blended analysis was revealed from the description ofhow the incidents were experienced by the participants. The final categories were what were the feelings, what was happening, and what was the enviromnent? The resulting transformation was initially only going to consider cognitive and affective changes, however, it was apparent that contextual changes also occurred for all participants, so this category was also included. The model was described with the construction metaphor of a building "foimdation" to illustrate the variety of conditions that are necessary for transformative learning to occur. Since this was an exploratory study, no prior models or processes were used in data analysis, however, it appeared that the model developed from this study incorporated existing models and provided a more encompassing life picture oftransformative learning.

Modeling Stock Order Flows and Learning Market-Making from Data

Stock markets employ specialized traders, market-makers, designed to provide liquidity and volume to the market by constantly supplying both supply and demand. In this paper, we demonstrate a novel method for modeling the market as a dynamic system and a reinforcement learning algorithm that learns profitable market-making strategies when run on this model. The sequence of buys and sells for a particular stock, the order flow, we model as an Input-Output Hidden Markov Model fit to historical data. When combined with the dynamics of the order book, this creates a highly non-linear and difficult dynamic system. Our reinforcement learning algorithm, based on likelihood ratios, is run on this partially-observable environment. We demonstrate learning results for two separate real stocks.

Implicit learning: Below the subjective threshold?

In this review, we consider three possible criteria by which knowledge might be regarded as implicit or inaccessible: It might be implicit only in the sense that it is difficult to articulate freely, or it might be implicit according to either an objective threshold or a subjective threshold. We evaluate evidence for these criteria in relation to artificial grammar learning, the control of complex systems, and sequence learning, respectively. We argue that the convincing evidence is not yet in, but construing the implicit nature of implicit learning in terms of a subjective threshold is most likely to prove fruitful for future research. Furthermore, the subjective threshold criterion may demarcate qualitatively different types of knowledge. We argue that (1) implicit, rather than explicit, knowledge is often relatively inflexible in transfer to different domains, (2) implicit, rather than explicit, learning occurs when attention is focused on specific items and not underlying rules, and (3) implicit learning and the resulting knowledge are often relatively robust.