Essays about: "LSTMs"

Showing result 1 - 5 of 31 essays containing the word LSTMs.

  1. 1. Forecasting With Feature-Based Time Series Clustering

    University essay from Jönköping University/Tekniska Högskolan

    Author : Conrad Tingström; Johan Åkerblom Svensson; [2023]
    Keywords : demand forecasting; time series prediction; time series clustering;

    Abstract : Time series prediction plays a pivotal role in various areas, including for example finance, weather forecasting, and traffic analysis. In this study, time series of historical sales data from a packaging manufacturer is used to investigate the effects that clustering such data has on forecasting performance. READ MORE

  3. 2. Temporal Localization of Representations in Recurrent Neural Networks

    University essay from Högskolan Dalarna/Institutionen för information och teknik

    Author : Asadullah Najam; [2023]
    Keywords : Recurrent Neural Networks RNNs ; Deep Learning; Time Series Prediction; Exploding Values; Gradient Decay; Long Short-Term Memory LSTMs ; Gated Recurrent Units GRUs ; Attention Mechanism; Moving Representations; Localizing Representations;

    Abstract : Recurrent Neural Networks (RNNs) are pivotal in deep learning for time series prediction, but they suffer from 'exploding values' and 'gradient decay,' particularly when learning temporally distant interactions. Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) have addressed these issues to an extent, but the precise mitigating mechanisms remain unclear. READ MORE

  4. 3. Unsupervised Machine Learning Based Anomaly Detection in Stockholm Road Traffic

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Vilma Hellström; [2023]
    Keywords : Anomaly detection; DBSCAN; LSTM; Machine learning; Synthetic anomalies; Unsupervised learning; Anomalidetektering; DBSCAN; LSTM; maskininlärning; syntetiska anomalier; oövervakad inlärning;

    Abstract : This thesis is a study of anomaly detection in vehicle traffic data in central Stockholm. Anomaly detection is an important tool in the analysis of traffic data for improved urban planing. Two unsupervised machine learning models are used, the DBSCAN clustering model and the LSTM deep learning neural network. READ MORE

  5. 4. Insurance Fraud Detection using Unsupervised Sequential Anomaly Detection

    University essay from Linköpings universitet/Institutionen för datavetenskap

    Author : Anton Hansson; Hugo Cedervall; [2022]
    Keywords : Insurance Fraud Detection; Anomaly Detection; Long Short-Term Memory Networks LSTM ; Unsupervised Learning; Autoencoder AE ; Variational Autoencoder VAE ; Interpretable Machine Learning; Feature Engineering; Feature Selection; Feature Importance;

    Abstract : 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. READ MORE

  6. 5. Geospatial Trip Data Generation Using Deep Neural Networks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Aditya Deepak Udapudi; [2022]
    Keywords : Deep Learning; Geospatial; Generative Adversarial Network GAN ; Deep Learning; Geospatial; Generativa Motståndsnätverk GAN ;

    Abstract : Development of deep learning methods is dependent majorly on availability of large amounts of high quality data. To tackle the problem of data scarcity one of the workarounds is to generate synthetic data using deep learning methods. READ MORE