Continual learning on nano drones

Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize the autonomous robots industry sector thanks to their very small form factor. The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for the on-board computations. Therefore, traditional computer vision and control algorithms are too computationally expensive to be executed on board these palm-sized robots, and we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight pipelines for autonomous tasks. However, relying on deep learning exposes us to the problem of generalization since the deployment scenario of a convolutional neural network (CNN) is often composed by different visual cues and different features from those learned during training, leading to poor inference performances. Our objective is to develop and deploy and adaptation algorithm, based on the concept of latent replays, that would allow us to fine-tune a CNN to work in new and diverse deployment scenarios. To do so we start from an existing model for visual human pose estimation, called PULPFrontnet, which is used to identify the pose of a human subject in space through its 4 output variables, and we present the design of our novel adaptation algorithm, which features automatic data gathering and labeling and on-device deployment. We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment scenarios, improving the R2 scores of the four network outputs, with respect to an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1]. Finally we demonstrate how it is possible to fine-tune our neural network in real time (i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip on board the nano-drone, and we show how all adaptation operations can take place using less than 2mWh of energy, a small fraction of the available battery power.

Na "periferia" da quadra : educação fisica, cultura e sociabilidade na escola

Universidade Estadual de Campinas . Faculdade de Educação Física

Students' collective knowledge construction in the virtual learning environment ""ToLigado - your school interactive newspaper""

Introduction. The ToLigado Project - Your School Interactive Newspaper is an interactive virtual learning environment conceived, developed, implemented and supported by researchers at the School of the Future Research Laboratory of the University of Sao Paulo, Brazil. Method. This virtual learning environment aims to motivate trans-disciplinary research among public school students and teachers in 2,931 schools equipped with Internet-access computer rooms. Within this virtual community, students produce collective multimedia research documents that are immediately published in the portal. The project also aims to increase students' autonomy for research, collaborative work and Web authorship. Main sections of the portal are presented and described. Results. Partial results of the first two years' implementation are presented and indicate a strong motivation among students to produce knowledge despite the fragile hardware and software infrastructure at the time. Discussion. In this new environment, students should be seen as 'knowledge architects' and teachers as facilitators, or 'curiosity managers'. The ToLigado portal may constitute a repository for future studies regarding student attitudes in virtual learning environments, students' behaviour as 'authors', Web authorship involving collective knowledge production, teachers' behaviour as facilitators, and virtual learning environments as digital repositories of students' knowledge construction and social capital in virtual learning communities.

Evaluation of gastrointestinal motility in awake rats: a learning exercise for undergraduate biomedical students

Souza MA, Souza MH, Palheta RC Jr, Cruz PR, Medeiros BA, Rola FH, Magalhaes PJ, Troncon LE, Santos AA. Evaluation of gastrointestinal motility in awake rats: a learning exercise for undergraduate biomedical students. Adv Physiol Educ 33: 343-348, 2009; doi: 10.1152/advan.90176.2008.-Current medical curricula devote scarce time for practical activities on digestive physiology, despite frequent misconceptions about dyspepsia and dysmotility phenomena. Thus, we designed a hands-on activity followed by a small-group discussion on gut motility. Male awake rats were randomly submitted to insulin, control, or hypertonic protocols. Insulin and control rats were gavage fed with 5% glucose solution, whereas hypertonic-fed rats were gavage fed with 50% glucose solution. Insulin treatment was performed 30 min before a meal. All meals (1.5 ml) contained an equal mass of phenol red dye. After 10, 15, or 20 min of meal gavage, rats were euthanized. Each subset consisted of six to eight rats. Dye recovery in the stomach and proximal, middle, and distal small intestine was measured by spectrophotometry, a safe and reliable method that can be performed by minimally trained students. In a separate group of rats, we used the same protocols except that the test meal contained (99m)Tc as a marker. Compared with control, the hypertonic meal delayed gastric emptying and gastrointestinal transit, whereas insulinic hypoglycemia accelerated them. The session helped engage our undergraduate students in observing and analyzing gut motor behavior. In conclusion, the fractional dye retention test can be used as a teaching tool to strengthen the understanding of basic physiopathological features of gastrointestinal motility.

E-Learning Used in a Training Course on Atraumatic Restorative Treatment (ART) for Brazilian Dentists

The purpose of this study was to assess the benefits of using e-learning resources in a dental training course on Atraumatic Restorative Treatment (ART). This e-course was given in a DVD format, which presented the ART technique and philosophy. The participants were twenty-four dentists from the Brazilian public health system. Prior to receiving the DVD, the dentists answered a questionnaire regarding their personal data, previous knowledge about ART, and general interest in training courses. The dentists also participated in an assessment process consisting of a test applied before and after the course. A single researcher corrected the tests, and intraexaminer reproducibility was calculated (kappa=0.89). Paired t-tests were carried out to compare the means between the assessments, showing a significant improvement in the performance of the subjects on the test taken after the course (p<0.05). A linear regression model was used with the difference between the means as the outcome. A greater improvement on the test results was observed among female dentists (p=0.034), dentists working for a shorter period of time in the public health system (p=0.042), and dentists who used the ART technique only for urgent and/or temporary treatment (p=0.010). In conclusion, e-learning has the potential of improving the knowledge that dentists working in the public health system have about ART, especially those with less clinical experience and less knowledge about the subject.

LEARNING A COMPLEX MOTOR SKILL FROM VIDEO AND POINT-LIGHT DEMONSTRATIONS

The aim of this Study was to compare the learning process of a highly complex ballet skill following demonstrations of point light and video models 16 participants divided into point light and video groups (ns = 8) performed 160 trials of a pirouette equally distributed in blocks of 20 trials alternating periods of demonstration and practice with a retention test a day later Measures of head and trunk oscillation coordination d1 parity from the model and movement time difference showed similarities between video and point light groups ballet experts evaluations indicated superiority of performance in the video over the point light group Results are discussed in terms of the task requirements of dissociation between head and trunk rotations focusing on the hypothesis of sufficiency and higher relevance of information contained in biological motion models applied to learning of complex motor skills

Contuse lesion of the rat spinal cord of moderate intensity leads to a higher time-dependent secondary neurodegeneration than severe one - An open-window for experimental neuroprotective interventions

Secondary neurodegeneration takes place in the surrounding tissue of spinal cord trauma and modifies substantially the prognosis, considering the small diameter of its transversal axis. We analyzed neuronal and glial responses in rat spinal cord after different degree of contusion promoted by the NYU Impactor. Rats were submitted to vertebrae laminectomy and received moderate or severe contusions. Control animals were sham operated. After 7 and 30 days post surgery, stereological analysis of Nissl staining cellular profiles showed a time progression of the lesion volume after moderate injury, but not after severe injury. The number of neurons was not altered cranial to injury. However, same degree of diminution was seen in the caudal cord 30 days after both severe and moderate injuries. Microdensitometric image analysis demonstrated a microglial reaction in the white matter 30 days after a moderate contusion and showed a widespread astroglial reaction in the white and gray matters 7 days after both severities. Astroglial activation lasted close to lesion and in areas related to Wallerian degeneration. Data showed a more protracted secondary degeneration in rat spinal cord after mild contusion, which offered an opportunity for neuroprotective approaches. Temporal and regional glial responses corroborated to diverse glial cell function in lesioned spinal cord. (C) 2007 Elsevier Ltd. All rights reserved.

Time Constraints in the School Environment: What Does a Sleepy Student Tell Us?

In this article, we discuss school schedules and their implications in the context of chronobiological contemporary knowledge, arguing for the need to reconsider time planning in the school setting. We present anecdotal observations regarding chronobiological challenges imposed by the school system throughout different ages and discuss the effects of these schedules in terms of sleepiness and its deleterious consequences on learning, memory, and attention. Different settings (including urban vs. rural habitats) influence timing, which also depends on self-selected sleep schedules. Finally, we criticize the traditional view of a necessary strict stability of sleep-wake habits.

Constant-random practice and the adaptive process in motor learning with varying amounts of constant practice

The adaptive process in motor learning was examined in terms of effects of varying amounts of constant practice performed before random practice. Participants pressed five response keys sequentially, the last one coincident with the lighting of a final visual stimulus provided by a complex coincident timing apparatus. Different visual stimulus speeds were used during the random practice. 33 children (M age=11.6 yr.) were randomly assigned to one of three experimental groups: constant-random, constant-random 33%, and constant-random 66%. The constant-random group practiced constantly until they reached a criterion of performance stabilization three consecutive trials within 50 msec. of error. The other two groups had additional constant practice of 33 and 66%, respectively, of the number of trials needed to achieve the stabilization criterion. All three groups performed 36 trials under random practice; in the adaptation phase, they practiced at a different visual stimulus speed adopted in the stabilization phase. Global performance measures were absolute, constant, and variable errors, and movement pattern was analyzed by relative timing and overall movement time. There was no group difference in relation to global performance measures and overall movement time. However, differences between the groups were observed on movement pattern, since constant-random 66% group changed its relative timing performance in the adaptation phase.

Real-Time Voltage Regulation in Power Distribution System Using Fuzzy Control

Two different fuzzy approaches to voltage control in electric power distribution systems are introduced in this paper. The real-time controller in each case would act on power transformers equipped with under-load tap changers. Learning systems are employed to turn the voltage-control relays into adaptive devices. The scope of this study has been limited to the power distribution substation, and the voltage measurements and control actions are carried out on the secondary bus. The capacity of fuzzy systems to handle approximate data, together with their unique ability to interpret qualitative information, make it possible to design voltage-control strategies that satisfy the requirements of the Brazilian regulatory bodies and the real concerns of the electric power distribution companies. Fuzzy control systems based on these two strategies have been implemented and the test results were highly satisfactory.

Accelerating autonomous learning by using heuristic selection of actions

This paper investigates how to make improved action selection for online policy learning in robotic scenarios using reinforcement learning (RL) algorithms. Since finding control policies using any RL algorithm can be very time consuming, we propose to combine RL algorithms with heuristic functions for selecting promising actions during the learning process. With this aim, we investigate the use of heuristics for increasing the rate of convergence of RL algorithms and contribute with a new learning algorithm, Heuristically Accelerated Q-learning (HAQL), which incorporates heuristics for action selection to the Q-Learning algorithm. Experimental results on robot navigation show that the use of even very simple heuristic functions results in significant performance enhancement of the learning rate.

On Building a Memory Evolutive System for Application to Learning and Cognition Modeling

We address here aspects of the implementation of a memory evolutive system (MES), based on the model proposed by A. Ehresmann and J. Vanbremeersch (2007), by means of a simulated network of spiking neurons with time dependent plasticity. We point out the advantages and challenges of applying category theory for the representation of cognition, by using the MES architecture. Then we discuss the issues concerning the minimum requirements that an artificial neural network (ANN) should fulfill in order that it would be capable of expressing the categories and mappings between them, underlying the MES. We conclude that a pulsed ANN based on Izhikevich`s formal neuron with STDP (spike time-dependent plasticity) has sufficient dynamical properties to achieve these requirements, provided it can cope with the topological requirements. Finally, we present some perspectives of future research concerning the proposed ANN topology.

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.

Triple objective team mentoring: achieving learning objectives with chemical engineering students

A sophisticated style of mentoring has been found to be essential to support engineering student teams undertaking technically demanding, real-world problems as part of a Project-Centred Curriculum (PCC) at The University of Queensland. The term ‘triple-objective’ mentoring was coined to define mentoring that addresses not only the student’s technical goal achievement but also their time and team management. This is achieved through a number of formal mentor meetings that are informed by a confidential instrument which requires students to individually reflect on team processes prior to the meeting, and a checklist of technical requirements against which the interim student team progress and achievements are assessed. Triple-objective mentoring requires significant time input and coordination by the academic but has been shown to ensure effective student team work and learning undiminished by team dysfunction. Student feedback shows they value the process and agree that the tools developed to support the process are effective in developing and assessing team work and skills with average scores mostly above 3 on a four point scale.

A randomized trial of a problem-based learning approach for teaching epidemiology

Purpose. To conduct a controlled trial of traditional and problem-based learning (PBL) methods of teaching epidemiology. Method. All second-year medical students (n = 136) at The University of Western Australia Medical School were offered the chance to participate in a randomized controlled trial of teaching methods fur an epidemiology course. Students who consented to participate (n = 80) were randomly assigned to either a PBL or a traditional course. Students who did not consent or did not return the consent form (n = 56) were assigned to the traditional course, Students in both streams took identical quizzes and exams. These scores, a collection of semi-quantitative feedback from all students, and a qualitative analysis of interviews with a convenience sample of six students from each stream were compared. Results. There was no significant difference in performances on quizzes or exams between PBL and traditional students. Students using PBL reported a stronger grasp of epidemiologic principles, enjoyed working with a group, and, at the end of the course, were more enthusiastic about epidemiology and its professional relevance to them than were students in the traditional course. PBL students worked more steadily during the semester but spent only marginally more time on the epidemiology course overall. Interviews corroborated these findings. Non-consenting students were older (p < 0.02) and more likely to come from non-English-speaking backgrounds (p < 0.005). Conclusions. PBL provides an academically equivalent but personally far richer learning experience. The adoption of PBL approaches to medical education makes it important to study whether PBL presents particular challenges for students whose first language is not the language of instruction.