Sökning: "RNN-modeller"
Hittade 5 uppsatser innehållade ordet RNN-modeller.
1. Exploration and Evaluation of RNN Models on Low-Resource Embedded Devices for Human Activity Recognition
Master-uppsats, KTH/Mekatronik och inbyggda styrsystemSammanfattning : 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. LÄS MER
2. Remaining Useful Life Prediction of Power Electronic Devices Using Recurrent Neural Networks
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The growing demand for sustainable technology has led to an increased application of power electronics. As these devices are often exposed to harsh conditions, their reliability is a primary concern for both manufacturers and users. LÄS MER
3. Sequential Deep Learning Models for Neonatal Sepsis Detection : A suitability assessment of deep learning models for event detection in physiological data
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Sepsis is a life-threatening condition that neonatal patients are especially susceptible to. Fortunately, improved bedside monitoring has enabled the collection and use of continuous vital signs data for the purpose of detecting conditions such as sepsis. LÄS MER
4. Predicting average response sentiments to mass sent emails using RNN
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This study is concerned with using the popular Recurrent Neural Network (RNN) model, and its variants Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM), on the novel problem of Sentiment Forecasting (SF). The goal of SF is to predict what the sentiment of a response will be in a conversation, using only the previous utterance. LÄS MER
5. Spelling Correction in a Music Entity Search Engine by Learning from Historical Search Queries
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Query spelling correction is an important component of modern search engines that can help users to express their intent, and thus improve search quality. In this study, we investigated with what accuracy a sequence-to-sequence recurrent neural network (RNN) can recognise and correct misspellings in a music search engine, when the model is trained with old search queries. LÄS MER