Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 109 for “"LSTMs"”.
-
Short term temperature forecasting using LSTMS, and CNN
Weather forecasting is a vital application in present times. We can use the predictions to minimize the weather related loss. Use of machine learning and deep learning algorithms for forecasting, can eliminate or reduce the necessity of big data and high computation dependent process of …
-
Looking under the hood: visualizing what LSTMs learn
… of what recurrent networks, particularly LSTMs, learn in the domain of action recognition, where the inputs are sequences of 3D human poses, or skeletons. The goal of the thesis is to understand the properties learned by a network with regard to an input action sequence, and how it will …
-
Deep Reinforcement Learning, LSTMs & Pointers for DL Scheduling in LTE
Downlink scheduling in LTE is an open problem for which several heuristic solutions exist. Recently, there has been an increase in interest in applying machine learning to networking problems, including downlink scheduling. Improvements in Physical Layer capabilities have generated new …
-
Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs
… of neural networks, we suggest using Variational LSTMs to make the speed forecasts. This Recurrent Neural Network uses Dropout to produce a Bayesian approximation and generate probabilistic outputs. This thesis also investigates the effects of inclement weather on traffic breakdown probability and …
-
Human Path Prediction Using Auto Encoder LSTMs and Single Temporal Encoders
… problem of frame prediction is Auto Encoder LSTMs. Though there are many implementations of this, at its core, it is a neural network comprised of a series of time sensitive processing blocks that shrink and then grow the data’s dimensions to make a prediction. The idea of using Auto Encoder …
-
Utilizing GAN and Sequence Based LSTMs on Post-RF Metadata for Near Real Time Analysis
Wireless anomaly detection is a mature field with several unique solutions. This thesis aims to describe a novel way of detecting wireless anomalies using metadata analysis based methods. The metadata is processed and analyzed by a LSTM based Autoencoder and a LSTM based feature analyzer to produce …
-
Learning from videos with deep convolutional LSTM networks
… This research explores the use of convolution LSTMs to simultaneously learn spatial- and temporal-information in videos. A deep network of convolutional LSTMs allows the model to access the entire range of temporal information at all spatial scales of the data. This work first constructs an …
-
Application of Conventional Feedforward and Deep Neural Networks to Power Distribution System State Estimation and State Forecasting
… (CNNs) and long short-term memory networks (LSTMs) to mitigate challenges in power distribution system state estimation and forecasting based upon conventional analytic methods. The ability of MLPs to perform regression to perform power system state estimation will be investigated. MLPs are …
-
Time series forecasting with applications to finance
… deep learning-based algorithms such RNNs, LSTMs, GRUs, TCNs, and bidirectional LSTMs and GRUs for predicting stock prices. We perform a comprehensive study and present all the experimental results on different datasets. We find that ARIMA and GRU perform better for single-step stock price …
-
Methods for working with DNA methylation data in lightweight cancer diagnosis classification models
… (RNNs), Long Short-Term Memory networks (LSTMs), and XGBoost—were trained and evaluated using grid-searched hyperparameters and categorized into Light, Medium, and Heavy complexity tiers. Experimental results show that XGBoost consistently outperformed RNNs and LSTMs across both datasets, …
-
Evaluating Transformer's Ability to Learn Mildly Context-Sensitive Languages
… data and have comparable performance to LSTMs, and learn highly interpretable self-attention patterns. However, such transformers cannot consistently recognize strings from the languages that are longer than the ones seen during training, and are often outperformed by LSTMs in this …
-
Moving object path prediction for traffic scenes
… specifically Long Short-Term Memory Networks (LSTMs), due to their ability to process this type of data. LSTMs have the limitation of only predicting a single path per tracklet. Path prediction requires predicting with a level of uncertainty. Predicting multiple future paths instead of a single …
-
Differential Recurrent Neural Networks for Human Activity Recognition
… hidden states. Unfortunately, the conventional LSTMs do not consider the impact of spatio-temporal dynamics corresponding to the given salient motion patterns, when they gate the information that ought to be memorized through time. To address this problem, we propose a differential gating scheme …
-
Streamflow in flux: LSTM modeling of pre- and post-fire hydrology in the United States
… first known near-continental-scale effort to use LSTMs to learn and extract hydrologic response to fire. Three LSTM models were trained on different temporal splits of 15-year periods containing a fire event. One LSTM model was trained on pre-fire data, a second model on post-fire data, and a …
-
Gendered Neural Networks: Representation and generalisation of grammatical gender in language models
… and LSTM language models, particularly LSTMs, effectively handle grammatical gender agreement in French, even in complex long-distance constructions with attractors. We demonstrate that this ability is supported by a highly sparse encoding mechanism in LSTMs, with distinct gender units …
-
Embedding based clustering of time series data using dynamic time warping
… we use the state-of-the-art autoencoders with LSTMs, Bidirectional LSTMs and GRUs to learn highly non-linear mapping functions by training the networks with subsequences of timeseries to perform data reconstruction. Next, we extract the trained encoders to generate embeddings which are …
-
Assessing the Robustness of Deep Learning Streamflow Models Under Climate Change
… (the NOAA National WaterModel), and found that LSTMs were generally more accurate than both, even when trained on climatologically biased data splits. The process-based model did not show as large of a performance gap as the conceptual and deep learning models, however (i) this model was not …
-
Enhancing LSTM streamflow modeling in data-scarce rain-dominated basins: the impact of using multiple precipitation products as model inputs
… approach for streamflow modeling.To train LSTMs, daily meteorological forcings (e.g., precipitation, temperature, radiation) alongside static catchment attributes (e.g., geophysical and climatological) are typically required. Large-sample datasets such as CARAVAN have enabled the global …
-
ABOVEGROUND BIOMASS DENSITY ESTIMATION USING DEEP LEARNING: INSIGHT FROM NEON GROUND-TRUTH DATA AND SIMULATED GEDI WAVEFORM
… simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly …
-
Latent Compositional Representations for English Function Word Comprehension
… tree-compositional models perform as well as LSTMs, but lag behind BERT to varying degrees between tasks. Context-dependent behavior of tree-compositional models highlights a potential weakness of the architecture in the absence of grounding information.
Page 1 of 6