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 19 of 19 for “"Sequence modeling"”.
-
Understanding stories via event sequence modeling
Understanding stories, i.e. sequences of events, is a crucial yet challenging natural language understanding (NLU) problem, which requires dealing with multiple aspects of semantics, including actions, entities and emotions, as well as background knowledge. In this thesis, towards the goal of …
-
Neural Sequence Modeling for Domain-Specific Language Processing: A Systematic Approach
In recent years, deep learning based sequence modeling (neural sequence modeling) techniques have made substantial progress in many tasks, including information retrieval, question answering, information extraction, machine translation, etc. Benefiting from the highly scalable attention-based …
-
A study of Bluetooth Frequency Hopping sequence : modeling and a practical attack
… this work, we investigate the Frequency Hopping sequence and specifically the hop selection kernel. We analyze the operation of the kernel hardware by partitioning it into three parts. Based on this modeling, we propose an attacking method for the hop selection kernel. The proposed method shows …
-
Compositional Models for Few Shot Sequence Learning
Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data—particularly to rare or unseen subsequences. Past work has found symbolic …
-
Deep Generative Models for Trajectory Prediction and Mobility Network Forecasting
… model that treats trajectories as token sequences and employs spatially constrained beam search to predict each individuals’s next k locations with high precision. Building on these forecasts, we present MobiNetForecast, which constructs and predicts the future topology of the mobility …
-
Decision Transformer-based Traveling Salesman Tour Generation
… environments into transformer-compatible sequence-modeling problems. By modeling a TSP instance as an graph-based environment with states and actions, we can input partial tours into the Decision Transformer to infer the next best action in an autoregressive fashion. With the power of the …
-
Quasimetric decision transformer: enhancing goal-conditioned reinforcement learning with structured distance guidance
… promising results in offline RL by leveraging sequence modeling. However, standard DTs rely on Returns-to-Go (RTG) tokens, which are heuristically defined and often suboptimal for goal-conditioned tasks. In this work, we introduce Quasimetric Decision Transformer (QuaD), a novel approach that …
-
The Effect Of Hyperparameters In The Activation Layers Of Deep Neural Networks
… including image recognition, speech recognition, sequence modeling, and natural language processing. Many of most exciting recent deep neural network studies have made improvements by hardcoding less about the network and giving the neural network more control over its own parameters, allowing …
-
Meta-Learning Exploration Strategies with Decision Transformers
… ICPE leverages the in-context learning and sequence-modeling capabilities of transformers, combined with supervised learning and deep reinforcement learning techniques to learn exploration strategies directly from experience. Through extensive experiments on synthetic and semi-synthetic …
-
scPhen: Single-Cell Phenotype Predictor for Alzheimer’s Disease
… heterogeneity, offering a powerful substrate for modeling disease circuitry. However, predicting patient-level phenotypes from scRNA-seq remains challenging due to limited sample sizes, variable cell counts, and the computational burden of modeling long-context dependencies. We present scPhen, a …
-
Reinforcement learning with natural language signals
… of solving Natural Language problems, similar to Sequence-to-Sequence models, but using multistage reasoning. We use Long Short-Term Memory Networks to parse the Natural Language input, whose final hidden state is used to compute action scores for the Deep Q-learning algorithm. First part of the …
-
Music signal processing for automatic extraction of harmonic and rhythmic information
… probabilistic approaches that include acoustic modeling layer and language modeling layer. We investigate the usage of standard N-grams and Factored Language Models (FLM) for automatic chord recognition. Another central topic of this work is the feature extraction techniques. We develop a set of …
-
Data analysis in proteomics novel computational strategies for modeling and interpreting complex mass spectrometry data
… is developed suitable for use in spectral modeling. Finally, a general machine learning approach is developed based on conditional random fields (CRFs). These models are capable of dealing with arbitrary sequence modeling tasks, similar to hidden Markov models (HMMs), but are far more …
-
Language-Grounded Post-Completion Mistake Detection in Procedural Videos
… The method grounds video executions into step sequences, compares raw step descriptions, semantic role representations, and action--object abstractions, and verifies the resulting traces with a Hidden Markov Model. Across CaptainCook4D, EgoPER, EgoOops, and auxiliary Assembly101 experiments, …
-
Generalizing Under Data Scarcity. Enhancing the representation capability from few samples.
… avoided. By reframing few-shot learning as a sequence modeling problem, we analyze the generalization capabilities of in-context learners across domains, and study how training order influences performance. We propose the GEOM framework for supervised few-shot classification and extend its …
-
Modeling audio and visual cues for real-world event detection
… This research emphasizes generalizable robust modeling of single-microphone audio cues and/or single-camera visual cues for the detection of real-world events, requiring no expensive annotation other than the known timestamps of the training events. To model the audio cues for event detection, …
-
The Influence of AR Head-Mounted Displays on Spatial Perception and Worker Response in Construction Training
… Independent Component Analysis, and regression modeling to identify hemispheric differences and misalignments between perceived safety and actual psychophysiological responses. Objective 3 advances the framework into predictive modeling, using the same haptic-frame environment, deep learning …
-
On the study of various methods for domain generalization and inverse problems
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Detekce maligních domén s využitím AI
Malígne domény predstavujú vážnu hrozbu pre kybernetickú bezpečnosť, keďže sa zneužívajú na šírenie škodlivého kódu, uskutočňovanie phishingových útokov a komunikáciu s napadnutými systémami prostredníctvom domén generovaných algoritmami (DGA). Cieľom tejto práce je navrhnúť a vyhodnotiť modely pre …