Spelling suggestions: "subject:"recurrent neural network"" "subject:"decurrent neural network""
91 |
A comparative study of Neural Network Forecasting models on the M4 competition dataRidhagen, Markus, Lind, Petter January 2021 (has links)
The development of machine learning research has provided statistical innovations and further developments within the field of time series analysis. This study seeks to investigate two different approaches on artificial neural network models based on different learning techniques, and answering how well the neural network approach compares with a basic autoregressive approach, as well as how the artificial neural network models compare to each other. The models were compared and analyzed in regards to the univariate forecast accuracy on 20 randomly drawn time series from two different time frequencies from the M4 competition dataset. Forecasting was made dependent on one time lag (t-1) and forecasted three and six steps ahead respectively. The artificial neural network models outperformed the baseline Autoregressive model, showing notably lower mean average percentage error overall. The Multilayered perceptron models performed better than the Long short-term memory model overall, whereas the Long short-term memory model showed improvement on longer prediction time dimensions. As the training were done univariately on a limited set of time steps, it is believed that the one layered-approach gave a good enough approximation on the data, whereas the added layer couldn’t fully utilize its strengths of processing power. Likewise, the Long short-term memory model couldn’t fully demonstrate the advantagements of recurrent learning. Using the same dataset, further studies could be made with another approach to data processing. Implementing an unsupervised approach of clustering the data before analysis, the same models could be tested with multivariate analysis on models trained on multiple time series simultaneously.
|
92 |
Using a Character-Based Language Model for Caption Generation / Användning av teckenbaserad språkmodell för generering av bildtextKeisala, Simon January 2019 (has links)
Using AI to automatically describe images is a challenging task. The aim of this study has been to compare the use of character-based language models with one of the current state-of-the-art token-based language models, im2txt, to generate image captions, with focus on morphological correctness. Previous work has shown that character-based language models are able to outperform token-based language models in morphologically rich languages. Other studies show that simple multi-layered LSTM-blocks are able to learn to replicate the syntax of its training data. To study the usability of character-based language models an alternative model based on TensorFlow im2txt has been created. The model changes the token-generation architecture into handling character-sized tokens instead of word-sized tokens. The results suggest that a character-based language model could outperform the current token-based language models, although due to time and computing power constraints this study fails to draw a clear conclusion. A problem with one of the methods, subsampling, is discussed. When using the original method on character-sized tokens this method removes characters (including special characters) instead of full words. To solve this issue, a two-phase approach is suggested, where training data first is separated into word-sized tokens where subsampling is performed. The remaining tokens are then separated into character-sized tokens. Future work where the modified subsampling and fine-tuning of the hyperparameters are performed is suggested to gain a clearer conclusion of the performance of character-based language models.
|
93 |
Explainable AI For Predictive MaintenanceKarlsson, Nellie, Bengtsson, My January 2022 (has links)
As the complexity of deep learning model increases, the transparency of the systems does the opposite. It may be hard to understand the predictions a deep learning model makes, but even harder to understand why these predictions are made. Using eXplainable AI (XAI), we can gain greater knowledge of how the model operates and how the input in which the model receives can change its predictions. In this thesis, we apply Integrated Gradients (IG), an XAI method primarily used on image data and on datasets containing tabular and time-series data. We also evaluate how the results of IG differ from various types of models and how the change of baseline can change the outcome. In these results, we observe that IG can be applied to both sequenced and nonsequenced data, with varying results. We can see that the gradient baseline does not affect the results of IG on models such as RNN, LSTM, and GRU, where the data contains time series, as much as it does for models like MLP with nonsequenced data. To confirm this, we also applied IG to SVM models, which gave the results that the choice of gradient baseline has a significant impact on the results of IG.
|
94 |
PhD ThesisJunghoon Kim (15348493) 26 April 2023 (has links)
<p> </p>
<p>In order to advance next-generation communication systems, it is critical to enhance the state-of-the-art communication architectures, such as device-to-device (D2D), multiple- input multiple-output (MIMO), and intelligent reflecting surface (IRS), in terms of achieving high data rate, low latency, and high energy efficiency. In the first part of this dissertation, we address joint learning and optimization methodologies on cutting-edge network archi- tectures. First, we consider D2D networks equipped with MIMO systems. In particular, we address the problem of minimizing the network overhead in D2D networks, defined as the sum of time and energy required for processing tasks at devices, through the design for MIMO beamforming and communication/computation resource allocation. Second, we address IRS-assisted communication systems. Specifically, we study an adaptive IRS control scheme considering realistic IRS reflection behavior and channel environments, and propose a novel adaptive codebook-based limited feedback protocol and learning-based solutions for codebook updates. </p>
<p><br></p>
<p>Furthermore, in order for revolutionary innovations to emerge for future generations of communications, it is crucial to explore and address fundamental, long-standing open problems for communications, such as the design of practical codes for a variety of important channel models. In the later part of this dissertation, we study the design of practical codes for feedback-enabled communication channels, i.e., feedback codes. The existing feedback codes, which have been developed over the past six decades, have been demonstrated to be vulnerable to high forward/feedback noises, due to the non-triviality of the design of feedback codes. We propose a novel recurrent neural network (RNN) autoencoder-based architecture to mitigate the susceptibility to high channel noises by incorporating domain knowledge into the design of the deep learning architecture. Using this architecture, we suggest a new class of non-linear feedback codes that increase robustness to forward/feedback noise in additive White Gaussian noise (AWGN) channels with feedback. </p>
|
95 |
Unauthorised Session Detection with RNN-LSTM Models and Topological Data Analysis / Obehörig Sessionsdetektering med RNN-LSTM-Modeller och Topologisk DataanalysMaksymchuk Netterström, Nazar January 2023 (has links)
This thesis explores the possibility of using session-based customers data from Svenska Handelsbanken AB to detect fraudulent sessions. Tools within Topological Data Analysis are employed to analyse customers behavior and examine topological properties such as homology and stable rank at the individual level. Furthermore, a RNN-LSTM model is, on a general behaviour level, trained to predict the customers next event and investigate its potential to detect anomalous behavior. The results indicate that simplicial complexes and their corresponding stable rank can be utilized to describe differences between genuine and fraudulent sessions on individual level. The use of a neural network suggests that there are deviant behaviors on general level concerning the difference between fraudulent and genuine sessions. The fact that this project was done without internal bank knowledge of fraudulent behaviour or historical knowledge of general suspicious activity and solely by data handling and anomaly detection shows great potential in session-based detection. Thus, this study concludes that the use of Topological Data Analysis and Neural Networks for detecting fraud and anomalous events provide valuable insight and opens the door for future research in the field. Further analysis must be done to see how effectively one could detect fraud mid-session. / I följande uppsats undersöks möjligheten att använda sessionbaserad kunddata från Svenska Handelsbanken AB för att detektera bedrägliga sessioner. Verktyg inom Topologisk Dataanalys används för att analysera kunders beteende och undersöka topologiska egenskaper såsom homologi och stabil rang på individnivå. Dessutom tränas en RNN-LSTM modell på en generell beteende nivå för att förutsäga kundens nästa händelse och undersöka dess potential att upptäcka avvikande beteende. Resultaten visar att simpliciella komplex och deras motsvarande stabil rang kan användas för att beskriva skillnader mellan genuina och bedrägliga sessioner på individnivå. Användningen av ett neuralt nätverk antyder att det finns avvikande beteenden på en generell nivå avseende skillnaden mellan bedrägliga och genuina sessioner. Det faktum att detta projekt genomfördes utan intern bankkännedom om bedrägerier eller historisk kunskap om allmäna misstänksamma aktiviteter och enbart genom datahantering och anomalidetektion visar stor potential för sessionbaserad detektion. Därmed drar denna studie slutsatsen att användningen av topologisk dataanalys och neurala nätverk för att upptäcka bedrägerier och avvikande händelser ger värdefulla insikter och öppnar dörren för framtida fortsätta studier inom området. Vidare analyser måste göras för att se hur effektivt man kan upptäcka bedrägerier mitt i sessioner.
|
96 |
Safe Reinforcement Learning for Social Human-Robot Interaction : Shielding for Appropriate Backchanneling Behavior / Säker förstärkningsinlärning för social människa-robotinteraktion : Avskärmning för lämplig uppbackningsbeteendeAkif, Mohamed January 2023 (has links)
Achieving appropriate and natural backchanneling behavior in social robots remains a challenge in Human-Robot Interaction (HRI). This thesis addresses this issue by utilizing methods from Safe Reinforcement Learning in particular shielding to improve social robot backchanneling behavior. The aim of the study is to develop and implement a safety shield that guarantees appropriate backchanneling. In order to achieve that, a Recurrent Neural Network (RNN) is trained on a human-human conversational dataset. Two agents are built; one uses a random algorithm to backchannel and another uses shields on top of its algorithm. The two agents are tested using a recorded human audio, and later evaluated in a between-subject user study with 41 participants. The results did not show any statistical significance between the two conditions, for the chosen significance level of α < 0.05. However, we observe that the agent with shield had a better listening behavior, more appropriate backchanneling behavior and missed less backchanneling opportunities than the agent without shields. This could indicate that shields have a positive impact on the robot’s behavior. We discuss potential explanations for why we did not obtain statistical significance and shed light on the potential for further exploration. / Att uppnå lämpligt och naturligt upbbackningsbeteende i sociala robotar är fortfarande en utmaning i Människa-Robot Interaktion (MRI). Den här avhandlingen tar upp detta problem genom att använda metoder från säker förstärkningsinlärning i synnerhet avskärmning för att förbättra sociala robotars upbbackningsbeteende. Syftet med studien är att utveckla och implementera en säkerhetsavskärmning som garanterar lämplig upbbackning. För att uppnå det, tränas ett återkommande neuralt nätverk på en människa-människa konversationsdatamängd. Två agenter byggs; en använder en slumpmässig algoritm för att upbbacka och en annan använder avskärmninng ovanpå sin algoritm. De två agenterna testas med hjälp av ett inspelat mänskligt ljud och utvärderas senare i en användarstudie med 41 deltagare. Resultaten visade inte någon statistisk signifikans mellan de två skicken, för den valda signifikansnivån < 0, 05. Vi observerar dock att agenten med avskärmning hade ett bättre lyssningsbeteende, mer lämplig upbbackningsbeteende och missade mindre upbbacknings-möjligheter än agenten utan avskärmning. Detta kan indikera att avskärmning har en positiv inverkan på robotarnas beteende. Vi diskuterar potentiella förklaringar till varför vi inte fick statistisk signifikans och belyser potentialen för ytterligare utforskning.
|
97 |
Attention based Knowledge Tracing in a language learning settingVergunst, Sebastiaan January 2022 (has links)
Knowledge Tracing aims to predict future performance of users of learning platforms based on historical data, by modeling their knowledge state. In this task, the target is a binary variable representing the correctness of the exercise, where an exercise is a word uttered by the user. Current state-of-the-art models add attention layers to autoregressive models or rely on self-attention networks. However, these models are built on publicly available datasets that lack useful information about the interactions users have with exercises. In this work, various techniques are introduced that allow for the incorporation of additional information made available in a dataset provided by Astrid Education. They consist of encoding a time dimension, modeling the skill needed for each exercise explicitly, and adjusting the length of the interaction sequence. Introducing new information to the Knowledge Tracing framework allows Astrid to craft a more personalized experience for its users; thus fulfilling the purpose and goal of the thesis. Additionally, we perform experiments to understand what aspects influence the models. Results show that modeling the skills needed to solve an exercise using an encoding strategy and reducing the length of the interaction sequence lead to improvements in terms of both accuracy and AUC. The time-encoding did not lead to better results, further experimentation is needed to include the time dimension successfully. / Mänsklig kunskap är ett försök att förutsäga användarnas framtida prestanda på lärandeplattformar baserat på historiska data, genom att modellera deras kunskaps tillstånd. I denna uppgift är målet en binär variabel som representerar överensstämmelsen av övningen. Nuvarande state-of-the-art-modeller lägger till uppmärksamhetslager på autoregressiva modeller eller förlitar sig på self-attention-nätverk. Dessa modeller bygger dock på offentligt tillgängliga databaser som saknar användbar information om de interaktioner som användare har med övningar. I detta arbete introduceras olika tekniker som gör det möjligt att inkludera ytterligare information som görs tillgänglig i en databas som tillhandahålls av Astrid Education AB. De består av att koda en tidsdimension, modellera färdigheten som krävs för varje övning explicit och justera interaktionssekvenslängden. Genom att introducera ny information i ramverket för kunskapstracing tillåter Astrid att skapa en mer personlig upplevelse för sina användare; därmed uppfyller syftet och målet med denna avhandling. Dessutom genomför vi experiment för att förstå vilka aspekter som påverkar modellerna. Resultaten visar att modellering av färdigheter med en kodningsstrategi och reducering av interaktionssekvenslängden leder till förbättringar både vad gäller noggrannhet och AUC. Tidskodningen ledde inte till bättre resultat, ytterligare experimentering krävs för att inkludera tidsdimensionen på ett framgångsrikt sätt.
|
98 |
Enhancing failure prediction from timeseries histogram data : through fine-tuned lower-dimensional representationsJayaraman, Vijay January 2023 (has links)
Histogram data are widely used for compressing high-frequency time-series signals due to their ability to capture distributional informa-tion. However, this compression comes at the cost of increased di-mensionality and loss of contextual details from the original features.This study addresses the challenge of effectively capturing changesin distributions over time and their contribution to failure prediction.Specifically, we focus on the task of predicting Time to Event (TTE) forturbocharger failures.In this thesis, we propose a novel approach to improve failure pre-diction by fine-tuning lower-dimensional representations of bi-variatehistograms. The goal is to optimize these representations in a waythat enhances their ability to predict component failure. Moreover, wecompare the performance of our learned representations with hand-crafted histogram features to assess the efficacy of both approaches.We evaluate the different representations using the Weibull Time ToEvent - Recurrent Neural Network (WTTE-RNN) framework, which isa popular choice for TTE prediction tasks. By conducting extensive ex-periments, we demonstrate that the fine-tuning approach yields supe-rior results compared to general lower-dimensional learned features.Notably, our approach achieves performance levels close to state-of-the-art results.This research contributes to the understanding of effective failureprediction from time series histogram data. The findings highlightthe significance of fine-tuning lower-dimensional representations forimproving predictive capabilities in real-world applications. The in-sights gained from this study can potentially impact various indus-tries, where failure prediction is crucial for proactive maintenanceand reliability enhancement.
|
99 |
Classification of Repeated Measurement Data Using Growth Curves and Neural NetworksAndersson, Kasper January 2022 (has links)
This thesis focuses on statistical and machine learning methods designed for sequential and repeated measurement data. We start off by considering the classic general linear model (MANOVA) followed by its generalization, the growth curve model (GMANOVA), designed for analysis of repeated measurement data. By considering a binary classification problem of normal data together with the corresponding maximum likelihood estimators for the growth curve model, we demonstrate how a classification rule based on linear discriminant analysis can be derived which can be used for repeated measurement data in a meaningful way. We proceed to the topics of neural networks which serve as our second method of classification. The reader is introduced to classic neural networks and relevant subtopics are discussed. We present a generalization of the classic neural network model to the recurrent neural network model and the LSTM model which are designed for sequential data. Lastly, we present three types of data sets with an total of eight cases where the discussed classification methods are tested. / Den här uppsatsen introducerar klassificeringsmetoder skapade för data av typen upprepade mätningar och sekventiell data. Den klassiska MANOVA modellen introduceras först som en grund för den mer allmäna tillväxtkurvemodellen(GMANOVA), som i sin tur används för att modellera upprepade mätningar på ett meningsfullt sätt. Under antagandet av normalfördelad data så härleds en binär klassificeringsmetod baserad på linjär diskriminantanalys, som tillsammans med maximum likelihood-skattningar från tillväxtkurvemodellen ger en binär klassificeringsregel för data av typen upprepade mätningarn. Vi fortsätter med att introducera läsaren för klassiska neurala nätverk och relevanta ämnen diskuteras. Vi generaliserar teorin kring neurala nätverk till typen "recurrent" neurala nätverk och LSTM som är designade för sekventiell data. Avslutningsvis så testas klassificeringsmetoderna på tre typer av data i totalt åtta olika fall.
|
100 |
Distinguishing Behavior from Highly Variable Neural Recordings Using Machine LearningSasse, Jonathan Patrick 04 June 2018 (has links)
No description available.
|
Page generated in 0.0802 seconds