Learning with Kernels on Graphs: DAG-based kernels, data streams and RNA function prediction.

In many application domains data can be naturally represented as graphs. When the application of analytical solutions for a given problem is unfeasible, machine learning techniques could be a viable way to solve the problem. Classical machine learning techniques are defined for data represented in a vectorial form. Recently some of them have been extended to deal directly with structured data. Among those techniques, kernel methods have shown promising results both from the computational complexity and the predictive performance point of view. Kernel methods allow to avoid an explicit mapping in a vectorial form relying on kernel functions, which informally are functions calculating a similarity measure between two entities. However, the definition of good kernels for graphs is a challenging problem because of the difficulty to find a good tradeoff between computational complexity and expressiveness. Another problem we face is learning on data streams, where a potentially unbounded sequence of data is generated by some sources. There are three main contributions in this thesis. The first contribution is the definition of a new family of kernels for graphs based on Directed Acyclic Graphs (DAGs). We analyzed two kernels from this family, achieving state-of-the-art results from both the computational and the classification point of view on real-world datasets. The second contribution consists in making the application of learning algorithms for streams of graphs feasible. Moreover,we defined a principled way for the memory management. The third contribution is the application of machine learning techniques for structured data to non-coding RNA function prediction. In this setting, the secondary structure is thought to carry relevant information. However, existing methods considering the secondary structure have prohibitively high computational complexity. We propose to apply kernel methods on this domain, obtaining state-of-the-art results.

Sviluppo di un corso di ottica sulla piattaforma e-learning moodle

La tesi sviluppa un corso di ottica attraverso la piattaforma e-learning di Ateneo Moodle. L'obiettivo è la proposta di alcuni argomenti di Fisica attraverso una metodologia nuova implementata con tecnologie informatiche di recente sviluppo. La prospettiva è quella dell'adozione di questo modello per la costruzione di un corso di Fisica Generale. Le caratteristiche rilevanti di questo approccio multimediale nell'ambito degli insegnamenti scientifici sono l'interattività tra gli studenti ed il corso, non precludendo il confronto tra i partecipanti all'attività didattica e la modularità del servizio formativo. A tal fine sono state inserite nell'insegnamento diverse features Moodle per realizzare questa architettura didattica.

Il formato EPUB: accessibilità e utilizzo nel contesto e-learning

EPUB rappresenta attualmente uno dei formati più usati per distribuire pubblicazioni digitali (ebook): è uno standard aperto e libero, i cui scenari d'uso variano dall'utilizzo interno, da parte di editori e aziende di conversione, alle distribuzione e vendita. EPUB è basato sui principali standard web, come HTML5 e CSS ed è progettato per strutturare e renderizzare contenuto reflowable, ottimizzando così la presentazione per il sistema di lettura usato. L'uso di specifiche conosciute e ancora in fase di definizione assicura un alto livello di attenzione e una comunità vivace, ma introduce anche un certo livello di incertezza sui futuri sviluppi. Uno degli aspetti centrali di EPUB è l'apertura totale verso pratiche che rendano il contenuto accessibile a persone con disabilità. Questa apertura è dovuta in parte all'uso degli standard web sopracitati, ma anche dalla consapevolezza che il contenuto accessibile rappresenta un valore aggiunto di notevole entità sia per i fruitori (anche non disabili) sia per gli editori e gli autori (in termini di mercato), creando un circolo virtuoso. Un altro aspetto interessante di EPUB è il suo possibile uso nell'ambito e-learning. È stata creata una specifica (più precisamente un profilo) deputata esclusivamente a questo scopo: EDUPUB. Tale specifica è tuttora in una fase iniziale, poichè ancora in draft, ma può comunque risultare di sicuro interesse per tutti i soggetti già coinvolti nello sviluppo e nell'uso di EPUB e di tecnologie relative all'apprendimento elettronico.

Nuove metodologie di apprendimento digitale: Microlearning e mobile learning

La tesi tratta in modo approfondito le tipologie di apprendimento non tradizionale, ovvero in contesto non scolastico/universitario, focalizzandosi sull'importanza che hanno i dispositivi mobili come mezzo di aggiornamento e miglioramento costante delle conoscenze e abilità delle persone. Queste nuove metodologie sono chiamate microlearning e mobile learning, evoluzioni naturali dell'e-learning nate dall'esigenza di un apprendimento che non fosse più solo a distanza, ma applicabile al contesto mobile per rispecchiare le nuove esigenze delle persone.

Segmentazione e categorizzazione di oggetti mediante immagini depth e deep learning

Questo lavoro è iniziato con uno studio teorico delle principali tecniche di classificazione di immagini note in letteratura, con particolare attenzione ai più diffusi modelli di rappresentazione dell’immagine, quali il modello Bag of Visual Words, e ai principali strumenti di Apprendimento Automatico (Machine Learning). In seguito si è focalizzata l’attenzione sulla analisi di ciò che costituisce lo stato dell’arte per la classificazione delle immagini, ovvero il Deep Learning. Per sperimentare i vantaggi dell’insieme di metodologie di Image Classification, si è fatto uso di Torch7, un framework di calcolo numerico, utilizzabile mediante il linguaggio di scripting Lua, open source, con ampio supporto alle metodologie allo stato dell’arte di Deep Learning. Tramite Torch7 è stata implementata la vera e propria classificazione di immagini poiché questo framework, grazie anche al lavoro di analisi portato avanti da alcuni miei colleghi in precedenza, è risultato essere molto efficace nel categorizzare oggetti in immagini. Le immagini su cui si sono basati i test sperimentali, appartengono a un dataset creato ad hoc per il sistema di visione 3D con la finalità di sperimentare il sistema per individui ipovedenti e non vedenti; in esso sono presenti alcuni tra i principali ostacoli che un ipovedente può incontrare nella propria quotidianità. In particolare il dataset si compone di potenziali ostacoli relativi a una ipotetica situazione di utilizzo all’aperto. Dopo avere stabilito dunque che Torch7 fosse il supporto da usare per la classificazione, l’attenzione si è concentrata sulla possibilità di sfruttare la Visione Stereo per aumentare l’accuratezza della classificazione stessa. Infatti, le immagini appartenenti al dataset sopra citato sono state acquisite mediante una Stereo Camera con elaborazione su FPGA sviluppata dal gruppo di ricerca presso il quale è stato svolto questo lavoro. Ciò ha permesso di utilizzare informazioni di tipo 3D, quali il livello di depth (profondità) di ogni oggetto appartenente all’immagine, per segmentare, attraverso un algoritmo realizzato in C++, gli oggetti di interesse, escludendo il resto della scena. L’ultima fase del lavoro è stata quella di testare Torch7 sul dataset di immagini, preventivamente segmentate attraverso l’algoritmo di segmentazione appena delineato, al fine di eseguire il riconoscimento della tipologia di ostacolo individuato dal sistema.

Spatio-temporal credit assignment in population learning

Learning by reinforcement is important in shaping animal behavior, and in particular in behavioral decision making. Such decision making is likely to involve the integration of many synaptic events in space and time. However, using a single reinforcement signal to modulate synaptic plasticity, as suggested in classical reinforcement learning algorithms, a twofold problem arises. Different synapses will have contributed differently to the behavioral decision, and even for one and the same synapse, releases at different times may have had different effects. Here we present a plasticity rule which solves this spatio-temporal credit assignment problem in a population of spiking neurons. The learning rule is spike-time dependent and maximizes the expected reward by following its stochastic gradient. Synaptic plasticity is modulated not only by the reward, but also by a population feedback signal. While this additional signal solves the spatial component of the problem, the temporal one is solved by means of synaptic eligibility traces. In contrast to temporal difference (TD) based approaches to reinforcement learning, our rule is explicit with regard to the assumed biophysical mechanisms. Neurotransmitter concentrations determine plasticity and learning occurs fully online. Further, it works even if the task to be learned is non-Markovian, i.e. when reinforcement is not determined by the current state of the system but may also depend on past events. The performance of the model is assessed by studying three non-Markovian tasks. In the first task, the reward is delayed beyond the last action with non-related stimuli and actions appearing in between. The second task involves an action sequence which is itself extended in time and reward is only delivered at the last action, as it is the case in any type of board-game. The third task is the inspection game that has been studied in neuroeconomics, where an inspector tries to prevent a worker from shirking. Applying our algorithm to this game yields a learning behavior which is consistent with behavioral data from humans and monkeys, revealing themselves properties of a mixed Nash equilibrium. The examples show that our neuronal implementation of reward based learning copes with delayed and stochastic reward delivery, and also with the learning of mixed strategies in two-opponent games.

Spatio-temporal credit assignment in population learning

Learning by reinforcement is important in shaping animal behavior. But behavioral decision making is likely to involve the integration of many synaptic events in space and time. So in using a single reinforcement signal to modulate synaptic plasticity a twofold problem arises. Different synapses will have contributed differently to the behavioral decision and, even for one and the same synapse, releases at different times may have had different effects. Here we present a plasticity rule which solves this spatio-temporal credit assignment problem in a population of spiking neurons. The learning rule is spike time dependent and maximizes the expected reward by following its stochastic gradient. Synaptic plasticity is modulated not only by the reward but by a population feedback signal as well. While this additional signal solves the spatial component of the problem, the temporal one is solved by means of synaptic eligibility traces. In contrast to temporal difference based approaches to reinforcement learning, our rule is explicit with regard to the assumed biophysical mechanisms. Neurotransmitter concentrations determine plasticity and learning occurs fully online. Further, it works even if the task to be learned is non-Markovian, i.e. when reinforcement is not determined by the current state of the system but may also depend on past events. The performance of the model is assessed by studying three non-Markovian tasks. In the first task the reward is delayed beyond the last action with non-related stimuli and actions appearing in between. The second one involves an action sequence which is itself extended in time and reward is only delivered at the last action, as is the case in any type of board-game. The third is the inspection game that has been studied in neuroeconomics. It only has a mixed Nash equilibrium and exemplifies that the model also copes with stochastic reward delivery and the learning of mixed strategies.

Exploring the effectiveness of development research with a monitoring and learning approach

There is a growing demand for better understanding of the link between research, policy and practice in development. This article provides findings from a study that aimed to gain insights into how researchers engage with their non-academic partners. It draws on experiences from the National Centre of Competence in Research North-South programme, a development research network of Swiss, African, Asian and Latin American institutions. Conceptually, this study is concerned with research effectiveness as a means to identify knowledge useful for society. Research can be improved and adapted when monitoring the effects of interactions between researchers and non-academic partners. Therefore, a monitoring and learning approach was chosen. This study reveals researchers' strategies in engaging with non-academic partners and points to framing conditions considered decisive for soccessful interactions. It concludes that reserachrs need to systematically analyse the socio-political context in which they intervene. By providing insights from the ground and reflecting on them in the light of the latest theoretical concepts, this article contributes to the emerging literature founded on practice-based experience.

Reshaping Rural Extension: Learning for Sustainability (LforS): An Integrative and Learning-Based Advisory Approach for Rural Extension with Small-Scale Farmers

This publication offers concrete suggestions for implementing an integrative and learning-oriented approach to agricultural extension with the goal of fostering sustainable development. It targets governmental and non-governmental organisations, development agencies, and extension staff working in the field of rural development. The book looks into the conditions and trends that influence extension today, and outlines new challenges and necessary adaptations. It offers a basic reflection on the goals, the criteria for success and the form of a state-of-the-art approach to extension. The core of the book consists of a presentation of Learning for Sustainability (LforS), an example of an integrative, learning-oriented approach that is based on three crucial elements: stakeholder dialogue, knowledge management, and organizational development. Awareness raising and capacity building, social mobilization, and monitoring & evaluation are additional building blocks. The structure and organisation of the LforS approach as well as a selection of appropriate methods and tools are presented. The authors also address key aspects of developing and managing a learning-oriented extension approach. The book illustrates how LforS can be implemented by presenting two case studies, one from Madagascar and one from Mongolia. It addresses conceptual questions and at the same time it is practice-oriented. In contrast to other extension approaches, LforS does not limit its focus to production-related aspects and the development of value chains: it also addresses livelihood issues in a broad sense. With its focus on learning processes LforS seeks to create a better understanding of the links between different spheres and different levels of decision-making; it also seeks to foster integration of the different actors’ perspectives.

Identifying the Negative Stigma Associated with Having a Learning Disability

Those with learning disabilities (LDs) can be characterized as a minority group, and like most groups of minorities they face a distinct stigma by the larger population. While there iscurrently a lack of research in understanding LD stigma, it has become increasingly important given the push for inclusive classrooms settings. In this study it was hypothesized that regardlessof a participants’ gender, when participants were given a hypothetical description of a person that included information indicating that the individual has a LD, the participants would rate that individual less favorably. Results were consistent with the hypothesis. Participants perceived the hypothetical LD individual as being less attractive, less successful, less emotionally stable,and more open to new experiences when compared to those participants who were given the non-LD description. These results show a level of negative bias in our population towards those with LDs. It is hoped that this research will help address the goal of inclusion and equality for those with LDs and aid in finding ways to identify, address, and attenuate these stigmatizations within all aspects of our society.

Alteration in 5HT1A Receptor Activity from a Prenatal Exposure to Dexamethasone in a Stressed and Non-Stressed Adult Male Rat

Synthetic glucocorticoids (GC) are used as a clinical therapeutic to stimulate lung development in fetuses that present the risk of preterm delivery. Previous studies have shown that a prenatal exposure to Dexamethasone (DEX) causes a disturbance in normal GC mediation of neuritic outgrowth, cell signaling, and serotonergic systems. Our hypothesis is that a prenatal exposure to DEX during the third trimester of pregnancy alters 5HT1A receptor function. Pregnant dams were injected daily with 150μg/ml/kg of DEX from gestation day 14 through 19. Control dams were treated with and equal volume of saline. Swim stress followed by elevated plus maze testing was conducted on male rats an hour and a half prior to being sacrificed to induce postnatal acute stress. The non-stressed group was also tested and allowed to return to baseline before sacrifice. Hippocampi were analyzed using a radioligand-receptor binding assay and GTPγS35 incorporation (3H-MPPF antagonist and 8-OH-DPAT agonist, respectively). A significant increase in Kd was found in non-stressed DEX-exposed animals compared to non-stressed controls (p

Moving from sustainable management to sustainable governance of natural resources: The role of social learning processes in rural India, Bolivia and Mali

The present paper discusses a conceptual, methodological and practical framework within which the limitations of the conventional notion of natural resource management (NRM) can be overcome. NRM is understood as the application of scientific ecological knowledge to resource management. By including a consideration of the normative imperatives that arise from scientific ecological knowledge and submitting them to public scrutiny, ‘sustainable management of natural resources’ can be recontextualised as ‘sustainable governance of natural resources’. This in turn makes it possible to place the politically neutralising discourse of ‘management’ in a space for wider societal debate, in which the different actors involved can deliberate and negotiate the norms, rules and power relations related to natural resource use and sustainable development. The transformation of sustainable management into sustainable governance of natural resources can be conceptualised as a social learning process involving scientists, experts, politicians and local actors, and their corresponding scientific and non-scientific knowledges. The social learning process is the result of what Habermas has described as ‘communicative action’, in contrast to ‘strategic action’. Sustainable governance of natural resources thus requires a new space for communicative action aiming at shared, intersubjectively validated definitions of actual situations and the goals and means required for transforming current norms, rules and power relations in order to achieve sustainable development. Case studies from rural India, Bolivia and Mali explore the potentials and limitations for broadening communicative action through an intensification of social learning processes at the interface of local and external knowledge. Key factors that enable or hinder the transformation of sustainable management into sustainable governance of natural resources through social learning processes and communicative action are discussed.

Chronic stimulation of the globus pallidus internus for treatment of non-dYT1 generalized dystonia and choreoathetosis: 2-year follow up

OBJECT: The authors studied the long-term efficacy of deep brain stimulation (DBS) of the posteroventral lateral globus pallidus internus up to 2 years postoperatively in patients with primary non-DYT1 generalized dystonia or choreoathetosis. The results are briefly compared with those reported for DBS in DYT1 dystonia (Oppenheim dystonia), which is caused by the DYT1 gene. METHODS: Enrollment in this prospective expanded pilot study was limited to adult patients with severely disabling, medically refractory non-DYT1 generalized dystonia or choreoathetosis. Six consecutive patients underwent follow-up examinations at defined intervals of 3 months, 1 year, and 2 years postsurgery. There were five women and one man, and their mean age at surgery was 45.5 years. Formal assessments included both the Burke-Fahn-Marsden dystonia scale and the recently developed Unified Dystonia Rating Scale. Two patients had primary generalized non-DYT1 dystonia, and four suffered from choreoathetosis secondary to infantile cerebral palsy. Bilateral quadripolar DBS electrodes were implanted in all instances, except in one patient with markedly asymmetrical symptoms. There were no adverse events related to surgery. The Burke-Fahn-Marsden scores in the two patients with generalized dystonia improved by 78 and 71% at 3 months, by 82 and 69% at 1 year, and by 78 and 70% at 2 years postoperatively. This was paralleled by marked amelioration of disability scores. The mean improvement in Burke-Fahn-Marsden scores in patients with choreoathetosis was 12% at 3 months, 29% at 1 year, and 23% at 2 years postoperatively, which was not significant. Two of these patients thought that they had achieved marked improvement at 2 years postoperatively, although results of objective evaluations were less impressive. In these two patients there was a minor but stable improvement in disability scores. All patients had an improvement in pain scores at the 2-year follow-up review. Medication was tapered off in both patients with generalized dystonia and reduced in two of the patients with choreoathetosis. All stimulation-induced side effects were reversible on adjustment of the DBS settings. Energy consumption of the batteries was considerably higher than in patients with Parkinson disease. CONCLUSIONS: Chronic pallidal DBS is a safe and effective procedure in generalized non-DYT1 dystonia, and it may become the procedure of choice in patients with medically refractory dystonia. Postoperative improvement of choreoathetosis is more modest and varied, and subjective ratings of outcome may exceed objective evaluations.

An insulin infusion advisory system for type 1 diabetes patients based on non-linear model predictive control methods

In this paper, an Insulin Infusion Advisory System (IIAS) for Type 1 diabetes patients, which use insulin pumps for the Continuous Subcutaneous Insulin Infusion (CSII) is presented. The purpose of the system is to estimate the appropriate insulin infusion rates. The system is based on a Non-Linear Model Predictive Controller (NMPC) which uses a hybrid model. The model comprises a Compartmental Model (CM), which simulates the absorption of the glucose to the blood due to meal intakes, and a Neural Network (NN), which simulates the glucose-insulin kinetics. The NN is a Recurrent NN (RNN) trained with the Real Time Recurrent Learning (RTRL) algorithm. The output of the model consists of short term glucose predictions and provides input to the NMPC, in order for the latter to estimate the optimum insulin infusion rates. For the development and the evaluation of the IIAS, data generated from a Mathematical Model (MM) of a Type 1 diabetes patient have been used. The proposed control strategy is evaluated at multiple meal disturbances, various noise levels and additional time delays. The results indicate that the implemented IIAS is capable of handling multiple meals, which correspond to realistic meal profiles, large noise levels and time delays.

E-mail-“inspired” changes in non-native legal discourse

At IDC, students use electronic resources for research and online interactive communication with instructors, usually in English. This paper discusses preliminary research into the overlap between the informality of e-mail communication between students and instructors and the growing use (or misuse) of e-mail-type informal discourse in formal written legal assignments. Four students were given a hypothetical legal case and requested to write: (a) a formal letter that would be sent by e-mail to one of the parties in the case, and (b) an executive memo e-mail to the senior partner in one of the law firms representing the parties. No instruction was given as to constructing a formal legal letter or an executive memo. In the resulting e-mail communications, many examples of typical informal e-mail shorthand were used. The students were interviewed and were able to locate and change most of the errors in their letters. Several students expressed the belief that this type of “shorthand” is or should be acceptable when the formal message is an e-mail communication.