Les modèles de langue pré-entraînés ont montré leur efficacité dans beaucoup de tâches de traitement de la langue naturelle. Ces modèles peuvent capter des régularités générales d'une langue à partir d'un grand ensemble de textes, qui sont utiles dans la plupart des applications en traitement de langue naturelle. Dans ce mémoire, nous étudions les problèmes de dialogue, i.e. générer une réponse à un énoncé de l'utilisateur. Nous exploitons les modèles de langue pré-entraînés pour traiter différents aspects des systèmes de dialogue. Premièrement, les modèles de langue pré-entraînés sont entraînés and utilisés dans les systèmes de dialogue de différentes façons. Il n'est pas clair quelle façon est la plus appropriée. Pour le dialogue orienté-tâche, l’approche de l'état de l'art pour le suivi de l'état de dialogue (Dialogue State Tracking) utilise BERT comme encodeur et empile un autre réseau de neurones récurrent (RNN) sur les sorties de BERT comme décodeur. Dans ce cas, seul l'encodeur peut bénéficier des modèles de langue pré-entraînés. Dans la première partie de ce mémoire, nous proposons une méthode qui utilise un seul modèle BERT pour l'encodeur et le décodeur, permettant ainsi un ajustement de paramètres plus efficace. Notre méthode atteint une performance qui dépasse l'état de l'art. Pour la tâche de génération de réponses dans un chatbot, nous comparons 4 approches communément utilisées. Elles sont basées sur des modèles pré-entraînés et utilisent des objectifs et des mécanismes d'attention différents. En nous appuyant sur des expérimentations, nous observons l'impact de deux types de disparité qui sont largement ignorées dans la littérature: disparité entre pré-entraînement et peaufinage, et disparité entre peaufinage et génération de réponse. Nous montrons que l'impact de ces disparités devient évident quand le volume de données d’entraînement est limité. Afin de remédier à ce problème, nous proposons deux méthodes qui réduisent les disparités, permettant d'améliorer la performance. Deuxièmement, même si les méthodes basées sur des modèles pré-entraînés ont connu de grands succès en dialogue général, nous devons de plus en plus traiter le problème de dialogue conditionné, c'est-à-dire dialogue en relation à une certaine condition (qui peut désigner un personnage, un sujet, etc.). Des chercheurs se sont aussi intéressés aux systèmes de chatbot avec des habiletés de conversation multiples, i.e. chatbot capable de confronter différentes situations de dialogues conditionnés. Ainsi, dans la seconde partie de ce mémoire, nous étudions le problème de génération de dialogue conditionné. D'abord, nous proposons une méthode générale qui exploite non seulement des données de dialogues conditionnées, mais aussi des données non-dialogues (textes) conditionnées. Ces dernières sont beaucoup plus faciles à acquérir en pratique. Ceci nous permet d'atténuer le problème de rareté de données. Ensuite, nous proposons des méthodes qui utilisent le concept d'adaptateur proposé récemment dans la littérature. Un adaptateur permet de renforcer un système de dialogue général en lui donnant une habileté spécifique. Nous montrons que les adaptateurs peuvent encoder des habiletés de dialogue conditionné de façon stricte ou flexible, tout en utilisant seulement 6% plus de paramètres. Ce mémoire contient 4 travaux sur deux grands problèmes de dialogue: l'architecture inhérente du modèle de dialogue basé sur des modèles de langue pré-entraînés, et l'enrichissement d'un système de dialogue général pour avoir des habiletés spécifiques. Ces travaux non seulement nous permettent d'obtenir des performances dépassant de l'état de l'art, mais aussi soulignent l'importance de concevoir l'architecture du modèle pour bien correspondre à la tâche, plutôt que simplement augmenter le volume de données d'entraînement et la puissance de calcul brute. / Pre-trained language models (LMs) have shown to be effective in many NLP tasks. They can capture general language regularities from a large amount of texts, which are useful for most applications related to natural languages. In this thesis, we study the problems of dialogue, i.e. to generate a response to a user's utterance. We exploit pre-trained language models to deal with different aspects of dialogue systems. First, pre-trained language models have been trained and used in different ways in dialogue systems and it is unclear what is the best way to use pre-trained language models in dialogue. For task-oriented dialogue systems, the state-of-the-art framework for Dialogue State Tracking (DST) uses BERT as the encoder and stacks an RNN upon BERT outputs as the decoder. Pre-trained language models are only leveraged for the encoder. In the first part of the thesis, we investigate methods using a single BERT model for both the encoder and the decoder, allowing for more effective parameter updating. Our method achieves new state-of-the-art performance. For the task of response generation in generative chatbot systems, we further compare the 4 commonly used frameworks based on pre-trained LMs, which use different training objectives and attention mechanisms. Through extensive experiments, we observe the impact of two types of discrepancy: pretrain-finetune discrepancy and finetune-generation discrepancy (i.e. differences between pre-training and fine-tuning, and between fine-tuning and generation), which have not been paid attention to. We show that the impact of the discrepancies will surface when limited amount of training data is available. To alleviate the problem, we propose two methods to reduce discrepancies, yielding improved performance. Second, even though pre-training based methods have shown excellent performance in general dialogue generation, we are more and more faced with the problem of conditioned conversation, i.e. conversation in relation with some condition (persona, topic, etc.). Researchers are also interested in multi-skill chatbot systems, namely equipping a chatbot with abilities to confront different conditioned generation tasks. Therefore, in the second part of the thesis, we investigate the problem of conditioned dialogue generation. First, we propose a general method that leverages not only conditioned dialogue data, but also conditioned non-dialogue text data, which are much easier to collect, in order to alleviate the data scarcity issue of conditioned dialogue generation. Second, the concept of Adapter has been recently proposed, which adapts a general dialogue system to enhance some dialogue skill. We investigate the ways to learn a dialogue skill. We show that Adapter has enough capacity to model a dialogue skill for either loosely-conditioned or strictly-conditioned response generation, while using only 6% more parameters. This thesis contains 4 pieces of work relating to the two general problems in dialogue systems: the inherent architecture for dialogue systems based on pre-trained LMs, and enhancement of a general dialogue system for some specific skills. The studies not only propose new approaches that outperform the current state of the art, but also stress the importance of carefully designing the model architecture to fit the task, instead of simply increasing the amount of training data and the raw computation power.

Indiana University-Purdue University Indianapolis (IUPUI) / An RGBZ synthetic dataset consisting of five object classes in a variety of virtual environments and orientations was combined with a small sample of real-world image data and used to train the Mask R-CNN (MR-CNN) architecture in a variety of configurations. When the MR-CNN architecture was initialized with MS COCO weights and the heads were trained with a mix of synthetic data and real world data, F1 scores improved in four of the five classes: The average maximum F1-score of all classes and all epochs for the networks trained with synthetic data is F1∗ = 0.91, compared to F1 = 0.89 for the networks trained exclusively with real data, and the standard deviation of the maximum mean F1-score for synthetically trained networks is σ∗ = 0.015, compared to σ_F1 = 0.020 for the networks trained exclusively with real F1 data. Various backgrounds in synthetic data were shown to have negligible impact on F1 scores, opening the door to abstract backgrounds and minimizing the need for intensive synthetic data fabrication. When the MR-CNN architecture was initialized with MS COCO weights and depth data was included in the training data, the net- work was shown to rely heavily on the initial convolutional input to feed features into the network, the image depth channel was shown to influence mask generation, and the image color channels were shown to influence object classification. A set of latent variables for a subset of the synthetic datatset was generated with a Variational Autoencoder then analyzed using Principle Component Analysis and Uniform Manifold Projection and Approximation (UMAP). The UMAP analysis showed no meaningful distinction between real-world and synthetic data, and a small bias towards clustering based on image background.

No description available.

Autonomous driving is a rapidly changing industry and has recently become a heavily focused research topic for vehicle producing companies and research organizations. These autonomous vehicles are typically equipped with sensors such as Light Detection and Radar (LiDAR) in order to perceive their surroundings. The problem of detecting and classifying surrounding objects from the sensor data can be solved using different types of algorithms. Recently, machine learning solutions have been investigated. One problem with the machine learning approach is that the models usually require a substantial amount of labeled data, and labeling LiDAR data is a time-consuming process. A promising solution to this problem is utilizing Domain Adaptation (DA) methods. The DA methods can use labeled camera data, which are easier to label, in conjunction with unlabeled LiDAR data to improve the performance of machine learning models on LiDAR data. This thesis investigates and compares different DA methods that can be used for classification of LiDAR data. In this thesis, two image classification datasets with data of humans and vehicles were created. One dataset contains camera images, and the other dataset contains LiDAR intensity images. The datasets were used to train and test three methods: (1) a baseline method, which simply uses labeled camera images to train a model. (2) Correlation Alignment (CORAL), a DA method that aligns the covariance of camera features towards LiDAR features. (3) Deep Adaptation Network (DAN), a DA method that includes a maximum mean discrepancy computation between camera and LiDAR features within the objective function of the model. These methods were then evaluated based on the resulting confusion matrices, accuracy, recall, precision and F1-score on LiDAR data. The results showed that DAN was the best out of the three methods, reaching an accuracy of 87% while the baseline and CORAL only measured at 65% and 73%, respectively. The strong performance of DAN showed that there is potential for using DA methods within the field of autonomous vehicles. / Industrin för självkörande fordon är snabbt förändlig och har under de senaste åren fått ett enormt fokus från biltillverkare och forskningsorganisationer. De självkörande fordonen är oftast utrustade med sensorer som Light Detection and Radar (LiDAR) för att hjälpa fordonen förstå omgivningen. Klassificering och identifiering av omgivande objekt är ett problem som kan lösas med hjälp av olika slags algoritmer. Nyligen har lösningar som utnyttjar maskininlärning undersökts. Ett problem med dessa lösningar är att modellerna oftast kräver en enorm mängd annoterad data, och att annotera LiDAR-data är en kostsam process. En lösning till detta problem är att utnyttja metoder inom Domain Adaptation (DA). DA metoder kan utnyttja både annoterad kameradata samt oannoterad LiDAR-data för att förbättra modellernas prestanda på LiDAR-data. Den här avhandlingen undersöker och jämför olika metoder inom DA som kan användas för att klassificera LiDAR-data. I det här arbetet skapades två dataset som består av data från människor och fordon. Det ena datasettet innehöll kamerabilder och det andra innehöll LiDAR-intensitetsbilder. Dessa dataset användes för att träna och testa tre olika metoder: (1) en baselinemetod, som endast använde annoterade kamerabilder för att träna en modell. (2) Correlation Alignment (CORAL), en metod inom DA som justerar kovariansen hos kamerafeatures mot kovariansen hos LiDAR-features. (3) Deep Adaptation Network (DAN), en metod inom DA som lägger till en uträkning av maximum mean discrepancy mellan kamerafeatures och LiDAR-features i modellens optimeringskriterie. Metoderna bedömdes sedan beroende på deras förvirringsmatriser, träffsäkerhet, precision, täckning och F1-träffsäkerhet på LiDAR-data. Resultaten avslöjade att DAN presterade bäst av de tre metoderna och uppnåde 87% träffsäkerhet medan baselinemetoden och CORAL bara uppnådde 65% respektive 73%. DANs imponerande prestation visade att det finns potential för att använda metoder inom DA för självkörande fordon.

Dealing with low-resource languages is a challenging task, because of the absence of sufficient data to train machine-learning models to make predictions on these languages. One way to deal with this problem is to use data from higher-resource languages, which enables the transfer of learning from these languages to the low-resource target ones. The present study focuses on dependency parsing and part-of-speech tagging of low-resource languages belonging to the spoken genre, i.e., languages whose treebank data is transcribed speech. These are the following: Beja, Chukchi, Komi-Zyrian, Frisian-Dutch, and Cantonese. Our approach involves investigating different types of transfer languages, employing MACHAMP, a state-of-the-art parser and tagger that uses contextualized word embeddings, mBERT, and XLM-R in particular. The main idea is to explore how the genre, the language similarity, none of the two, or the combination of those affect the model performance in the aforementioned downstream tasks for our selected target treebanks. Our findings suggest that in order to capture speech-specific dependency relations, we need to incorporate at least a few genre-matching source data, while language similarity-matching source data are a better candidate when the task at hand is part-of-speech tagging. We also explore the impact of multi-task learning in one of our proposed methods, but we observe minor differences in the model performance.

No description available.

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.

[pt] Esta dissertação de mestrado consiste em um estudo avançado sobre aprendizado profundo por reforço visual para robôs autônomos através de técnicas de transferência de aprendizado. Os ambientes de simulação testados neste estudo são ambientes realistas complexos onde o robô tinha como desafio aprender e transferir conhecimento em diferentes contextos para aproveitar a experiência de ambientes anteriores em ambientes futuros. Este tipo de abordagem, além de agregar conhecimento ao robô autônomo, diminui o número de épocas de treinamento do algoritmo, mesmo em ambientes complexos, justificando o uso de técnicas de transferência de aprendizado. / [en] This master s thesis consists of an advanced study on deep learning by visual reinforcement for autonomous robots through transfer learning techniques. The simulation environments tested in this study are highly realistic environments where the challenge of the robot was to learn and tranfer knowledge in different contexts to take advantage of the experiencia of previous environments in future environments. This type of approach besides adding knowledge to the autonomous robot reduces the number of training epochs the algorithm, even in complex environments, justifying the use of transfer learning techniques.

In this paper an analysis is conducted regarding whether a higher classification accuracy of facial expressions are possible. The approach used is that the seven basic emotional states are combined into a binary classification problem. Five different machine learning algorithms are implemented: Support vector machines, Extreme learning Machine and three different Convolutional Neural Networks (CNN). The utilized CNN:S were one conventional, one based on VGG16 and transfer learning and one based on residual theory known as RESNET50. The experiment was conducted on two datasets, one small containing no contamination called JAFFE and one big containing contamination called FER2013. The highest accuracy was achieved with the CNN:s where RESNET50 had the highest classification accuracy. When comparing the classification accuracy with the state of the art accuracy an improvement of around 0.09 was achieved on the FER2013 dataset. This dataset does however include some ambiguities regarding what facial expression is shown. It would henceforth be of interest to conduct an experiment where humans classify the facial expressions in the dataset in order to achieve a benchmark.

Machine learning has seen a rapid progress the last couple of decades, with more and more powerful neural network models continuously being presented. These neural networks require large amounts of data to train them. Labelled data is especially in great demand, but due to the time consuming and costly nature of data labelling, there exists a scarcity for labelled data, whereas there usually is an abundance of unlabelled data. In some cases, data from a certain distribution, or domain, is labelled, whereas the data we actually want to optimise our model on is unlabelled and from another domain. This falls under the umbrella of domain adaptation and the purpose of this thesis is to train a network using domain-adversarial training on eye image datasets consisting of a labelled source domain and an unlabelled target domain, with the goal of performing well on target data, i.e., overcoming the domain gap. This was done on two different datasets: a proprietary dataset from Tobii with real images and the public U2Eyes dataset with synthetic data. When comparing domain-adversarial training to a baseline model trained conventionally on source data and a oracle model trained conventionally on target data, the proposed DAT-ResNet model outperformed the baseline on both datasets. For the Tobii dataset, DAT-ResNet improved the Huber loss by 22.9% and the Intersection over Union (IoU) by 7.6%, and for the U2Eyes dataset, DAT-ResNet improved the Huber loss by 67.4% and the IoU by 37.6%. Furthermore, the IoU measures were extended to also include the portion of predicted ellipsis with no intersection with the corresponding ground truth ellipsis – referred to as zero-IoUs. By this metric, the proposed model improves the percentage of zero-IoUs by 34.9% on the Tobii dataset and by 90.7% on the U2Eyes dataset. / Maskininlärning har sett en snabb utveckling de senaste decennierna med mer och mer kraftfulla neurala nätverk-modeller presenterades kontinuerligt. Dessa neurala nätverk kräver stora mängder data för att tränas. Data med etiketter är det framförallt stor efterfrågan på, men på grund av det är tidskrävande och kostsamt att etikettera data så finns det en brist på sådan data medan det ofta finns ett överflöd av data utan etiketter. I vissa fall så är data från en viss fördelning, eller domän, etiketterad, medan datan som vi faktiskt vill optimera vår modell efter saknar etiketter och är från en annan domän. Det här faller under området domänadaptering och målet med det här arbetet är att träna ett nätverk genom att använda domänmoststående träning på dataset med ögonbilder som har en källdomän med etiketter och en måldomän utan etiketter, där målet är att prestera bra på data från måldomänen, i.e., att lösa ett domänadapteringsproblem. Det här gjordes på två olika dataset: ett dataset som ägs av Tobii med riktiga ögonbilder och det offentliga datasetet U2Eyes med syntetiska bilder. När domänadapteringsmodellen jämförs med en basmodell tränad konventionellt på källdata och en orakelmodell tränad konventionellt på måldata, så utklassar den presenterade DAT-ResNet-modellen basmodellen på båda dataseten. På Tobii-datasetet så förbättrade DAT-ResNet förlusten med 22.9% och Intersection over Union (IoU):n med 7.6%, och på U2Eyes-datasetet, förbättrade DAT-ResNet förlusten med 67.4% och IoU:n med 37.6%. Dessutom så utökades IoU-måtten till att också innefatta andelen av förutspådda ellipser utan något överlapp med tillhörande grundsanningsellipser – refererat till som noll-IoU:er. Enligt detta mått så förbättrar den föreslagna modellen noll-IoU:erna med 34.9% på Tobii-datasetet och 90.7% på U2Eyes-datasetet.