V dnešnej dobe systémy rozpoznávania reči s veľkým slovníkom dosahujú pomerne vysoké presnosti. Za ich výsledkami však často stoja desiatky ba až stovky hodín manuálne oanotovaných trénovacích dát. Takéto dáta sú často bežne nedostupné alebo pre požadovaný jazyk vôbec neexistujú. Možným riešením je použitie bežne dostupných no menej kvalitných audiovizuálnych dát. Táto práca sa zaoberá technikou zpracovania práve takýchto dát a ich použitím pre trénovanie akustických modelov. Ďalej táto práca pojednáva o možnom využití týchto dát pre kontinuálne vylepšovanie modelov, kedže tieto dáta sú prakticky nevyčerpateľné. Pre tieto účely bol v rámci práce navrhnutý nový prístup pre výber dát.

Recurrent Neural Networks(RNNs) are powerful models that have obtained outstanding achievements in many sequence learning tasks. Despite their accomplishments, RNN models still suffer with long sequences during training. It is because error propagate backwards from output to input layers carrying gradient signals, and with long input sequence, issues like vanishing and exploding gradients can arise. This thesis reviews many current studies and existing architectures designed to circumvent the long-term dependency problems in backpropagation through time (BPTT). Mainly, we focus on the method proposed by Trinh et al. (2018) which uses semi- supervised learning method to alleviate the long-term dependency problems in BPTT. Despite the good results Trinh et al. (2018)’s model achieved, we suggest that the model can be further improved with a more systematic way of balancing auxiliary signals. In this thesis, we present our paper – RNNs with Private and Shared Representations for Semi-Supervised Learning – which is currently under review for AAAI-2019. We propose a semi-supervised RNN architecture with explicitly designed private and shared representations that regulates the gradient flow from auxiliary task to main task. / Les réseaux neuronaux récurrents (RNN) sont des modèles puissants qui ont obtenu des réalisations exceptionnelles dans de nombreuses tâches d’apprentissage séquentiel. Malgré leurs réalisations, les modèles RNN sou˙rent encore de longues séquences pendant l’entraî-nement. C’est parce que l’erreur se propage en arrière de la sortie vers les couches d’entrée transportant des signaux de gradient, et avec une longue séquence d’entrée, des problèmes comme la disparition et l’explosion des gradients peuvent survenir. Cette thèse passe en revue de nombreuses études actuelles et architectures existantes conçues pour contour-ner les problèmes de dépendance à long terme de la rétropropagation dans le temps (BPTT). Nous nous concentrons principalement sur la méthode proposée par cite Trinh2018 qui utilise une méthode d’apprentissage semi-supervisée pour atténuer les problèmes de dépendance à long terme dans BPTT. Malgré les bons résultats obtenus avec le modèle de cite Trinh2018, nous suggérons que le modèle peut être encore amélioré avec une manière plus systématique d’équilibrer les signaux auxiliaires. Dans cette thèse, nous présentons notre article - emph RNNs with Private and Shared Representations for Semi-Supervised Learning - qui est actuellement en cours de révision pour AAAI-2019. Nous propo-sons une architecture RNN semi-supervisée avec des représentations privées et partagées explicitement conçues qui régule le flux de gradient de la tâche auxiliaire à la tâche principale.

Block characters are often used when filling out forms, for example when writing ones personal number. The question of whether or not there is recoverable, biometric (identity related) information within individual digits of hand written personal numbers is then relevant. This thesis investigates the question by using both handcrafted features and extracting features via Deep learning (DL) models, and successively limiting the amount of available training samples. Some recent works using DL have presented semi-supervised methods using Generative adveserial network (GAN) generated data together with a modified Label smoothing regularization (LSR) function. Using this training method might improve performance on a baseline fully supervised model when doing authentication. This work additionally proposes a novel modified LSR function named Bootstrap label smooting regularizer (BLSR) designed to mitigate some of the problems of previous methods, and is compared to the others. The DL feature extraction is done by training a ResNet50 model to recognize writers of a personal numbers and then extracting the feature vector from the second to last layer of the network.Results show a clear indication of recoverable identity related information within the hand written (personal number) digits in boxes. Our results indicate an authentication performance, expressed in Equal error rate (EER), of around 25% with handcrafted features. The same performance measured in EER was between 20-30% when using the features extracted from the DL model. The DL methods, while showing potential for greater performance than the handcrafted, seem to suffer from fluctuation (noisiness) of results, making conclusions on their use in practice hard to draw. Additionally when using 1-2 training samples the handcrafted features easily beat the DL methods.When using the LSR variant semi-supervised methods there is no noticeable performance boost and BLSR gets the second best results among the alternatives.

A high quality and large scale training data-set is an important guarantee to teach an ideal classifier for image classification. Manually constructing a training data- set  with  appropriate  labels  is  an  expensive  and  time  consuming  task.    Active learning techniques have been used to improved the existing models by reducing the  number  of  required  annotations.    The  present  work  aims  to  investigate the  way  to  build  a  model  for  identifying  and  utilizing  potential  informative and  representativeness  unlabeled  samples.    To  this  end,  two  approaches  for deep image classification using active learning are proposed, implemented and evaluated.  The two versions of active leaning for deep image classification differ in  the  input  space  exploration  so  as  to  investigate  how  classifier  performance varies  when  automatic  labelization  on  the  high  confidence  unlabeled  samples is  performed.    Active  learning  heuristics  based  on  uncertainty  measurements on low confidence predicted samples,  a pseudo-labelization technique to boost active  learning  by  reducing  the  number  of  human  interactions  and  knowledge transferring  form  pre-trained  models,  are  proposed  and  combined  into  our methodology.  The experimental results on two benchmark image classification data-sets  verify  the  effectiveness  of  the  proposed  methodology.    In  addition, a  new  pool-based  active  learning  query  strategy  is  proposed.     Dealing  with retraining-based algorithms we define a ”forgetting event” to have occurred when an  individual  training  example  transitions  the  maximum  predicted  probability class over the course of retraining. We integrated the new approach with the semi- supervised learning method in order to tackle the above challenges and observedgood performance against existing methods. / En  högkvalitativ  och  storskalig  träningsdataset  är  en  viktig  garanti  för  att  bli en  idealisk  klassificerare  för  bildklassificering.     Att  manuellt  konstruera  en träningsdatasats  med  lämpliga  etiketter  är  en  dyr  och  tidskrävande  uppgift. Aktiv  inlärningstekniker  har  använts  för  att  förbättra  de  befintliga  modellerna genom att minska antalet nödvändiga annoteringar. Det nuvarande arbetet syftar till  att  undersöka  sättet  att  bygga  en  modell  för  att  identifiera  och  använda potentiella informativa och representativa omärkta prover.   För detta ändamål föreslås, genomförs och genomförs två metoder för djup bildklassificering med aktivt  lärande  utvärderas.      De  två  versionerna  av  aktivt  lärande  för  djup bildklassificering  skiljer  sig  åt  i  undersökningen  av  ingångsutrymmet  för  att undersöka hur klassificeringsprestanda varierar när automatisk märkning på de omärkta  proverna  med  hög  konfidens  utförs.   Aktiv  lärande  heuristik  baserad på  osäkerhetsmätningar  på  förutsagda  prover  med  låg  konfidens,  en  pseudo- märkningsteknik för att öka aktivt lärande genom att minska antalet mänskliga interaktioner  och  kunskapsöverföring  av  förutbildade  modeller,  föreslås  och kombineras   i   vår   metod.      Experimentella   resultat   på   två   riktmärken   för bildklassificering datauppsättningar verifierar effektiviteten hos den föreslagna metodiken.   Dessutom föreslås en ny poolbaserad aktiv inlärningsfrågestrategi. När  vi  använder  omskolningsbaserade  algoritmer  definierar  vi  en  ”glömmer händelse” som skulle ha inträffat när ett individuellt träningsexempel överskrider den maximala förutsagda sannolikhetsklassen under omskolningsprocessen.  Vi integrerade den nya metoden med den semi-övervakad inlärning för att hanteraovanstående utmaningar och observeras bra prestanda mot befintliga metoder.

To increase equity and inclusion for underserved and excluded Indigenous students, we must make efforts to mitigate the unique barriers they face. As their knowledge systems have been historically excluded and erased in Western science, we begin by reviewing the literature on the inclusion of Traditional Ecological Knowledge (TEK) in biology education and describe best practices. Next, to better understand how Native Hawaiian and other Pacific Islander (NHPI) students integrate into the scientific community, we used Social Influence Theory as a framework to measure NHPI student science identity, self-efficacy, alignment with science values, and belonging. We also investigated how students feel their ethnic and science identities interact. We found that NHPI students do not significantly differ from non-NHPI students in these measures of integration, and that NHPI students are varied in how they perceive their ethnic and science identities interact. Some students experience conflict between the two identities, while others view the two as having a strengthening relationship. Next, we describe a lesson plan created to include Hawaiian TEK in a biology class using best practices described in the literature. This is followed by an empirical study on how students were impacted by this lesson. We measured student integration into the science community using science identity, self-efficacy, alignment with science values, and belonging. We found no significant differences between NHPI and non-NHPI students. We also looked at student participation, and found that all students participated more on intervention days involving TEK and other ways of knowing than on non-intervention days. Finally, we describe qualitative findings on how students were impacted by the TEK interventions. We found students were predominantly positively impacted by the inclusion of TEK and discuss future adjustments that could be made using their recommendations. The last chapter describes how we used remote sensing to investigate land cover in a fenced and unfenced region of the Koʻolau Mountains on the island of Oahu. After mapping the biodiversity hotspot Management Unit of Koloa, we found that there is slighlty more bare ground, grass, and bare ground/low vegetation mix in fenced, and thereby ungulate-free areas, than those that were unfenced and had ungulates. Implications of these findings and suggestions for future research are discussed.

<p dir="ltr">Artificial Intelligence (AI) is anticipated to exert a considerable impact on the global Gross Domestic Product (GDP), with projections estimating a contribution of 13 trillion dollars by the year 2030 (IEEE Board of Directors, 2019). In light of this influence on economic, societal, and intellectual realms, it is imperative for Policy Makers to acquaint themselves with the ongoing developments and consequential impacts of AI. The exigency of their preparedness lies in the potential for AI to evolve in unpredicted directions should proactive measures not be promptly instituted.</p><p dir="ltr">This paper endeavors to address a pivotal research question: " Do United States Policy Makers have a sufficient knowledgebase to understand Responsible AI in relation to Machine Learning to pass Artificial Intelligence legislation; and if they do not, how should a pedological instructional framework be created to give them the necessary knowledge?" The pursuit of answers to this question unfolded through the systematic review, gap analysis, and formulation of an instructional framework specifically tailored to elucidate the intricacies of Machine Learning. The findings of this study underscore the imperative for policymakers to undergo educational initiatives in the realm of artificial intelligence. Such educational interventions are deemed essential to empower policymakers with the requisite understanding for formulating effective regulatory frameworks that ensure the development of Responsible AI. The ethical dimensions inherent in this technological landscape warrant consideration, and policymakers must be equipped with the necessary cognitive tools to navigate these ethical quandaries adeptly.</p><p dir="ltr">In response to this exigency, the present study has undertaken the design and development of an instructional framework. This framework is conceived as a strategic intervention to address the evident cognitive gap existing among policymakers concerning the nuances of AI. By imparting an understanding of AI-related concepts, the framework aspires to cultivate a more informed and discerning governance ethos among policymakers, thus contributing to the responsible and ethical deployment of AI technologies.</p>

[pt] O segmento offshore de produção de petróleo é o principal produtor nacional desse insumo. Nesse contexto, inspeções submarinas são cruciais para a manutenção preventiva dos equipamentos, que permanecem toda a vida útil em ambiente oceânico. A partir dos dados de imagem e sensor coletados nessas inspeções, especialistas são capazes de prevenir e reparar eventuais danos. Tal processo é profundamente complexo, demorado e custoso, já que profissionais especializados têm que assistir a horas de vídeos atentos a detalhes. Neste cenário, o presente trabalho explora o uso de modelos de classificação de imagens projetados para auxiliar os especialistas a encontrarem o(s) evento(s) de interesse nos vídeos de inspeções submarinas. Esses modelos podem ser embarcados no ROV ou na plataforma para realizar inferência em tempo real, o que pode acelerar o ROV, diminuindo o tempo de inspeção e gerando uma grande redução nos custos de inspeção. No entanto, existem alguns desafios inerentes ao problema de classificação de imagens de inspeção submarina, tais como: dados rotulados balanceados são caros e escassos; presença de ruído entre os dados; alta variância intraclasse; e características físicas da água que geram certas especificidades nas imagens capturadas. Portanto, modelos supervisionados tradicionais podem não ser capazes de cumprir a tarefa. Motivado por esses desafios, busca-se solucionar o problema de classificação de imagens submarinas a partir da utilização de modelos que requerem menos supervisão durante o seu treinamento. Neste trabalho, são explorados os métodos DINO (Self-DIstillation with NO labels, auto-supervisionado) e uma nova versão multi-label proposta para o PAWS (Predicting View Assignments With Support Samples, semi-supervisionado), que chamamos de mPAWS (multi-label PAWS). Os modelos são avaliados com base em sua performance como extratores de features para o treinamento de um classificador simples, formado por uma camada densa. Nos experimentos realizados, para uma mesma arquitetura, se obteve uma performance que supera em 2.7 por cento o f1-score do equivalente supervisionado. / [en] The offshore oil production segment is the main national producer of this input. In this context, underwater inspections are crucial for the preventive maintenance of equipment, which remains in the ocean environment for its entire useful life. From the image and sensor data collected in these inspections,experts are able to prevent and repair damage. Such a process is deeply complex, time-consuming and costly, as specialized professionals have to watch hours of videos attentive to details. In this scenario, the present work explores the use of image classification models designed to help experts to find the event(s) of interest in under water inspection videos. These models can be embedded in the ROV or on the platform to perform real-time inference,which can speed up the ROV, monitor notification time, and greatly reduce verification costs. However, there are some challenges inherent to the problem of classification of images of armored submarines, such as: balanced labeled data are expensive and scarce; the presence of noise among the data; high intraclass variance; and some physical characteristics of the water that achieved certain specificities in the captured images. Therefore, traditional supervised models may not be able to fulfill the task. Motivated by these challenges, we seek to solve the underwater image classification problem using models that require less supervision during their training. In this work, they are explorers of the DINO methods (Self-Distillation with NO labels, self-supervised) anda new multi-label version proposed for PAWS (Predicting View AssignmentsWith Support Samples, semi-supervised), which we propose as mPAWS (multi-label PAWS). The models are evaluated based on their performance as features extractors for training a simple classifier, formed by a dense layer. In the experiments carried out, for the same architecture, a performance was obtained that exceeds by 2.7 percent the f1-score of the supervised equivalent.

Image recognition is a subfield in computer vision, representing a set of methods for analyzing images. Image recognition systems allow computers to automatically find patterns and draw conclusions directly from images. The recent growth of the ecommerce fashion industry has sparked an increased interest from research community, and subsequently industry participants have started to apply image recognition technologies to automate various processes and applications like clothing categorization, attribute tagging, automatic product recommendations and many more. However, most research have been concerned with supervised learning, which require large labeled datasets. This thesis investigates an alternative approach which could potentially mitigate the reliance of large labeled datasets. Specifically, it investigates how Semi- Supervised Learning (SSL) compares to supervised learning in the context of fashion category classification. This thesis demonstrates that a state- of- the- art SSL method to train Deep Convolutional Neural Networks can provide very close accuracy to supervised learning by a margin of approximately 1 to 3 percent for the considered set of images. / Bildigenkänning är ett delområde inom datorseende, det representerar en uppsättning metoder för att analysera bilder. Bildigenkänningssystem tillåter datorer att automatiskt hitta mönster och dra slutsatser direkt från bilder. Den senaste tillväxten inom mode e- handeln har ökat forskningsintresset inom området, detta har bidragit till att aktörer på marknaden har börjat applicera bildigenkänningstekniker för att automatisera diverse processer och applikationer, som till exempel klädeskategorisering, märkning av attribut, automatiska produktrekommendationer med flera. Dock så har majoriteten av all forskning inom detta område har fokuserat på övervakad inlärning, vilket kräver stora annoterade dataset, den här uppsatsen undersöker istället en alternativ metod, som potentiellt kan minska beroendet på stora annoterade dataset. Specifikt så undersöks och jämförs semiövervakad inlärning med övervakad inlärning vid kategorisering av modebilder. Resultaten visar att en toppmodern semiövervakad inlärningsmetod för att träna ett djupt neuralt nätverk kan åstadkomma en precision väldigt nära övervakad inlärning, med en marginal på ungefär 1 till 3 procent för de använda modebilderna.

No description available.

No description available.