The dorsodorsal division (DD) of the teleost telencephalon has been implicated in memory processes similar to those associated with the mammalian hippocampus. The network connectivity and neural activity underlying this involvement have remained unclear. This thesis attempts to elucidate both. Attempts have been made to record the neural activity of DD neurons, but none have succeeded in correlating the recorded firing with any meaningful stimuli. In this thesis, I present single-unit electrophysiological recordings of DD neurons that reveal persistent activity in the form of up-states which are evoked by two modalities of naturalistic sensory stimuli – visual and electrosensory. The anatomy of DD was a little better understood than the neural activity. Recent anatomical work has shown that DD is strongly inter-connected with the cortical-like dorsolateral division (DL) of the pallium, re-inforcing its similarity to mammalian hippocampal structures. This same work has also revealed much of DD’s extrinsic connectivity. It was not, however, of a resolution fine enough to disambiguate the connections of the various DD subregions, nor to clarify the existence and structure of intrinsic DD connectivity. In this thesis, I further elucidate the connectivity of DD, by isolating its subregions. This was done by means of very small and precise neurotracer injections. These injections revealed strong recurrent connectivity within individual DD subregions, multiple pathways between DD and DL, and striking similarities between the connectivities of DL and DD and those of the mammalian dentate gyrus and CA3 respectively. From the results of these investigations I propose a model of homology between the teleost DD-DL loop and the putative pattern separation and completion networks contained in the mammalian cortico-hippocampal circuitry, as well as a role for the observed persistent activity in DD within this model. I further propose the dorsal teleost telencephalon as an excellent model system for the further study of the network mechanisms of pattern separation and completion.

abstract: Recent advancements in external memory based neural networks have shown promise in solving tasks that require precise storage and retrieval of past information. Re- searchers have applied these models to a wide range of tasks that have algorithmic properties but have not applied these models to real-world robotic tasks. In this thesis, we present memory-augmented neural networks that synthesize robot navigation policies which a) encode long-term temporal dependencies b) make decisions in partially observed environments and c) quantify the uncertainty inherent in the task. We extract information about the temporal structure of a task via imitation learning from human demonstration and evaluate the performance of the models on control policies for a robot navigation task. Experiments are performed in partially observed environments in both simulation and the real world / Dissertation/Thesis / Masters Thesis Computer Science 2018

Human activity data is typically represented as time series data, and RNNs, often with LSTM cells, are commonly used for recognition in this field. However, RNNs and LSTM-RNNs are often too resource-intensive for real-time applications on resource constrained devices, making them unsuitable. This thesis project is carried out at Wrlds AB, Stockholm. At Wrlds, all machine learning is run in the cloud, but they have been attempting to run their AI algorithms on their embedded devices. The main task of this project was to investigate alternative network structures to minimize the size of the networks to be used on human activity data. This thesis investigates the use of Fast GRNN, a deep learning algorithm developed by Microsoft researchers, to classify human activity on resource-constrained devices. The FastGRNN algorithm was compared to state-of-the-art RNNs, LSTM, GRU, and Simple RNN in terms of accuracy, classification time, memory usage, and energy consumption. This research is limited to implementing the FastRNN algorithm on Nordic SoCs using their SDK and TensorFlow Lite Micro. The result of this thesis shows that the proposed network has similar performance as LSTM networks in terms of accuracy while being both considerably smaller and faster, making it a promising solution for human activity recognition on embedded devices with limited computational resources and merits further investigation. / Rörelse igenkännings analys är oftast representerat av tidsseriedata där ett RNN modell meden LSTM arkitektur är oftast den självklara vägen att ta. Dock så är denna arkitektur väldigt resurskrävande för applikationer i realtid och gör att det uppstår problem med resursbegränsad hårdvara. Detta examensarbete är utfört i samarbete med Wrlds Technologies AB. På Wrlds så körs deras maskin inlärningsmodeller på molnet och lokalt på mobiltelefoner. Wrlds har nu påbörjat en resa för att kunna köra modeller direkt på små inbyggda system. Examensarbete kommer att utvärdera en FastGRNN som är en NN-arkitektur utvecklad av Microsoft i syfte att användas på resurs begränsad hårdvara. FastGRNN algoritmen jämfördes med andra högkvalitativa arkitekturer som RNNs, LSTM, GRU och en simpel RNN. Träffsäkerhet, klassifikationstid, minnesanvändning samt energikonsumtion användes för att jämföra dom olika varianterna. Detta arbete kommer bara att utvärdera en FastGRNN algoritm på en Nordic SoCs och kommer att användas deras SDK samt Tensorflow Lite Micro. Resultatet från detta examensarbete visar att det utvärderade nätverket har liknande prestanda som ett LSTM nätverk men också att nätverket är betydligt mindre i storlek och därmed snabbare. Detta betyder att ett FastGRNN visar lovande resultat för användningen av rörelseigenkänning på inbyggda system med begränsad prestanda kapacitet.

Negation is a common property of languages, in that there are few languages, if any, that lack means to revert the truth-value of a statement. A challenge to cross-lingual studies of negation lies in the fact that languages encode and use it in different ways. Although this variation has been extensively researched in linguistics, little has been done in automated language processing. In particular, we lack computational models of processing negation that can be generalized across language. We even lack knowledge of what the development of such models would require. These models however exist and can be built by means of existing cross-lingual resources, even when annotated data for a language other than English is not available. This thesis shows this in the context of detecting string-level negation scope, i.e. the set of tokens in a sentence whose meaning is affected by a negation marker (e.g. 'not'). Our contribution has two parts. First, we investigate the scenario where annotated training data is available. We show that Bi-directional Long Short Term Memory (BiLSTM) networks are state-of-the-art models whose features can be generalized across language. We also show that these models suffer from genre effects and that for most of the corpora we have experimented with, high performance is simply an artifact of the annotation styles, where negation scope is often a span of text delimited by punctuation. Second, we investigate the scenario where annotated data is available in only one language, experimenting with model transfer. To test our approach, we first build NEGPAR, a parallel corpus annotated for negation, where pre-existing annotations on English sentences have been edited and extended to Chinese translations. We then show that transferring a model for negation scope detection across languages is possible by means of structured neural models where negation scope is detected on top of a cross-linguistically consistent representation, Universal Dependencies. On the other hand, we found cross-lingual lexical information only to help very little with performance. Finally, error analysis shows that performance is better when a negation marker is in the same dependency substructure as its scope and that some of the phenomena related to negation scope requiring lexical knowledge are still not captured correctly. In the conclusions, we tie up the contributions of this thesis and we point future work towards representing negation scope across languages at the level of logical form as well.

<div>Textual emotion classification is a task in affective AI that branches from sentiment analysis and focuses on identifying emotions expressed in a given text excerpt. </div><div>It has a wide variety of applications that improve human-computer interactions, particularly to empower computers to understand subjective human language better. </div><div>Significant research has been done on this task, but very little of that research leverages one of the most emotion-bearing symbols we have used in modern communication: Emojis.</div><div>In this thesis, we propose several transformer-based models for emotion classification that processes emojis as input tokens and leverages pretrained models and uses them</div><div>, a model that processes Emojis as textual inputs and leverages DeepMoji to generate affective feature vectors used as reference when aggregating different modalities of text encoding. </div><div>To evaluate ReferEmo, we experimented on the SemEval 2018 and GoEmotions datasets, two benchmark datasets for emotion classification, and achieved competitive performance compared to state-of-the-art models tested on these datasets. Notably, our model performs better on the underrepresented classes of each dataset.</div>

In this master thesis, we implement a two-step anomaly detection mechanism for non-recurrent traffic congestions with data collected from public transport buses in Stockholm. We investigate the use of machine learning to model time series data with LSTMs and evaluate the results with a baseline prediction model. The anomaly detection algorithm embodies both collective and contextual expressivity, meaning it is capable of findingcollections of delayed buses and also takes the temporality of the data into account. Results show that the anomaly detection performance benefits from the lower prediction errors produced by the LSTM network. The intersection rule significantly decreases the number of false positives while maintaining the true positive rate at a sufficient level. The performance of the anomaly detection algorithm has been found to depend on the road segment it is applied to, some segments have been identified to be particularly hard whereas other have been identified to be easier than others. The performance of the best performing setup of the anomaly detection mechanism had a true positive rate of 84.3 % and a true negative rate of 96.0 %. / I den här masteruppsatsen implementerar vi en tvåstegsalgoritm för avvikelsedetektering för icke återkommande trafikstockningar. Data är insamlad från kollektivtrafikbussarna i Stockholm. Vi undersöker användningen av maskininlärning för att modellerna tidsseriedata med hjälp av LSTM-nätverk och evaluerar sedan dessa resultat med en grundmodell. Avvikelsedetekteringsalgoritmen inkluderar både kollektiv och kontextuell uttrycksfullhet, vilket innebär att kollektiva förseningar kan hittas och att även temporaliteten hos datan beaktas. Resultaten visar att prestandan hos avvikelsedetekteringen förbättras av mindre prediktionsfel genererade av LSTM-nätverket i jämförelse med grundmodellen. En regel för avvikelser baserad på snittet av två andra regler reducerar märkbart antalet falska positiva medan den höll kvar antalet sanna positiva på en tillräckligt hög nivå. Prestandan hos avvikelsedetekteringsalgoritmen har setts bero av vilken vägsträcka den tillämpas på, där några vägsträckor är svårare medan andra är lättare för avvikelsedetekteringen. Den bästa varianten av algoritmen hittade 84.3 % av alla avvikelser och 96.0 % av all avvikelsefri data blev markerad som normal data.

Title: Neural networks for automatic speaker, language, and sex identifica- tion Author: Bich-Ngoc Do Department: Institute of Formal and Applied Linguistics Supervisor: Ing. Mgr. Filip Jurek, Ph.D., Institute of Formal and Applied Linguistics and Dr. Marco Wiering, Faculty of Mathematics and Natural Sciences, University of Groningen Abstract: Speaker recognition is a challenging task and has applications in many areas, such as access control or forensic science. On the other hand, in recent years, deep learning paradigm and its branch, deep neural networks have emerged as powerful machine learning techniques and achieved state-of- the-art in many fields of natural language processing and speech technology. Therefore, the aim of this work is to explore the capability of a deep neural network model, recurrent neural networks, in speaker recognition. Our pro- posed systems are evaluated on TIMIT corpus using speaker identification task. In comparison with other systems in the same test conditions, our systems could not surpass reference ones due to the sparsity of validation data. In general, our experiments show that the best system configuration is a combination of MFCCs with their dynamic features and a recurrent neural network model. We also experiment recurrent neural networks and convo- lutional neural...

Dans les systèmes cognitifs, le rôle de la mémoire de travail est crucial pour le raisonnement visuel et la prise de décision. D’énormes progrès ont été réalisés dans la compréhension des mécanismes de la mémoire de travail humain/animal, ainsi que dans la formulation de différents cadres de réseaux de neurones artificiels à mémoire augmentée. L’objectif global de notre projet est de former des modèles de réseaux de neurones artificiels capables de consolider la mémoire sur une courte période de temps pour résoudre une tâche de mémoire et les relier à l’activité cérébrale des humains qui ont résolu la même tâche. Le projet est de nature interdisciplinaire en essayant de relier les aspects de l’intelligence artificielle (apprentissage profond) et des neurosciences. La tâche cognitive utilisée est la tâche N-back, très populaire en neurosciences cognitives dans laquelle les sujets sont présentés avec une séquence d’images, dont chacune doit être identifiée pour savoir si elle a déjà été vue ou non. L’ensemble de données d’imagerie fonctionnelle (IRMf) utilisé a été collecté dans le cadre du projet Courtois Neurmod. Nous étudions plusieurs variantes de modèles de réseaux neuronaux récurrents qui apprennent à résoudre la tâche de mémoire de travail N-back en les entraînant avec des séquences d’images. Ces réseaux de neurones entraînés optimisés pour la tâche de mémoire sont finalement utilisés pour générer des représentations de caractéristiques pour les images de stimuli vues par les sujets humains pendant leurs enregistrements tout en résolvant la tâche. Les représentations dérivées de ces réseaux de neurones servent ensuite à créer un modèle de codage pour prédire l’activité IRMf BOLD des sujets. On comprend alors la relation entre le modèle de réseau neuronal et l’activité cérébrale en analysant cette capacité prédictive du modèle dans différentes zones du cerveau impliquées dans la mémoire de travail. Ce travail présente une manière d’utiliser des réseaux de neurones artificiels pour modéliser le comportement et le traitement de l’information de la mémoire de travail du cerveau et d’utiliser les données d’imagerie cérébrale capturées sur des sujets humains lors de la tâche N-back pour potentiellement comprendre certains mécanismes de mémoire du cerveau en relation avec ces modèles de réseaux de neurones artificiels. / In cognitive systems, the role of working memory is crucial for visual reasoning and decision making. Tremendous progress has been made in understanding the mechanisms of the human/animal working memory, as well as in formulating different frameworks of memory augmented artificial neural networks. The overall objective of our project is to train artificial neural network models that are capable of consolidating memory over a short period of time to solve a memory task and relate them to the brain activity of humans who solved the same task. The project is of interdisciplinary nature in trying to bridge aspects of Artificial Intelligence (deep learning) and Neuroscience. The cognitive task used is the N-back task, a very popular one in Cognitive Neuroscience in which the subjects are presented with a sequence of images, each of which needs to be identified as to whether it was already seen or not. The functional imaging (fMRI) dataset used has been collected as a part of the Courtois Neurmod Project. We study multiple variants of recurrent neural network models that learn to remember input images across timesteps. These trained neural networks optimized for the memory task are ultimately used to generate feature representations for the stimuli images seen by the human subjects during their recordings while solving the task. The representations derived from these neural networks are then to create an encoding model to predict the fMRI BOLD activity of the subjects. We then understand the relationship between the neural network model and brain activity by analyzing this predictive ability of the model in different areas of the brain that are involved in working memory. This work presents a way of using artificial neural networks to model the behavior and information processing of the working memory of the brain and to use brain imaging data captured from human subjects during the N-back task to potentially understand some memory mechanisms of the brain in relation to these artificial neural network models.

Fraud is a common crime within the insurance industry, and insurance companies want to quickly identify fraudulent claimants as they often result in higher premiums for honest customers. Due to the digital transformation where the sheer volume and complexity of available data has grown, manual fraud detection is no longer suitable. This work aims to automate the detection of fraudulent claimants and gain practical insights into fraudulent behavior using unsupervised anomaly detection, which, compared to supervised methods, allows for a more cost-efficient and practical application in the insurance industry. To obtain interpretable results and benefit from the temporal dependencies in human behavior, we propose two variations of LSTM based autoencoders to classify sequences of insurance claims. Autoencoders can provide feature importances that give insight into the models' predictions, which is essential when models are put to practice. This approach relies on the assumption that outliers in the data are fraudulent. The models were trained and evaluated on a dataset we engineered using data from a Swedish insurance company, where the few labeled frauds that existed were solely used for validation and testing. Experimental results show state-of-the-art performance, and further evaluation shows that the combination of autoencoders and LSTMs are efficient but have similar performance to the employed baselines. This thesis provides an entry point for interested practitioners to learn key aspects of anomaly detection within fraud detection by thoroughly discussing the subject at hand and the details of our work. / <p>Gjordes digitalt via Zoom. </p>

<p>The Ensemble Kalman filter (EnKF) has achieved great successes in data assimilation in atmospheric and oceanic sciences, but its failure in convergence to the right filtering distribution precludes its use for uncertainty quantification. Other existing methods, such as particle filter or sequential importance sampler, do not scale well to the dimension of the system and the sample size of the datasets. In this dissertation, we address these difficulties in a coherent way.</p><p><br></p><p> </p><p>In the first part of the dissertation, we reformulate the EnKF under the framework of Langevin dynamics, which leads to a new particle filtering algorithm, the so-called Langevinized EnKF (LEnKF). The LEnKF algorithm inherits the forecast-analysis procedure from the EnKF and the use of mini-batch data from the stochastic gradient Langevin-type algorithms, which make it scalable with respect to both the dimension and sample size. We prove that the LEnKF converges to the right filtering distribution in Wasserstein distance under the big data scenario that the dynamic system consists of a large number of stages and has a large number of samples observed at each stage, and thus it can be used for uncertainty quantification. We reformulate the Bayesian inverse problem as a dynamic state estimation problem based on the techniques of subsampling and Langevin diffusion process. We illustrate the performance of the LEnKF using a variety of examples, including the Lorenz-96 model, high-dimensional variable selection, Bayesian deep learning, and Long Short-Term Memory (LSTM) network learning with dynamic data.</p><p><br></p><p> </p><p>In the second part of the dissertation, we focus on two extensions of the LEnKF algorithm. Like the EnKF, the LEnKF algorithm was developed for Gaussian dynamic systems containing no unknown parameters. We propose the so-called stochastic approximation- LEnKF (SA-LEnKF) for simultaneously estimating the states and parameters of dynamic systems, where the parameters are estimated on the fly based on the state variables simulated by the LEnKF under the framework of stochastic approximation. Under mild conditions, we prove the consistency of resulting parameter estimator and the ergodicity of the SA-LEnKF. For non-Gaussian dynamic systems, we extend the LEnKF algorithm (Extended LEnKF) by introducing a latent Gaussian measurement variable to dynamic systems. Those two extensions inherit the scalability of the LEnKF algorithm with respect to the dimension and sample size. The numerical results indicate that they outperform other existing methods in both states/parameters estimation and uncertainty quantification.</p>