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 46 for “"sequence to sequence"”.
-
Improving Attention-based Sequence-to-sequence Models
… achieved state-of-the-art performance in various sequence-to-sequence tasks, including Neural Machine Translation (NMT), Automatic Speech Recognition (ASR) and speech synthesis, also known as Text-To-Speech (TTS). These models are often autoregressive, which leads to high modeling capacity, but …
-
Forecasting Energy Consumption using Sequence to Sequence Attention models
To combat negative environmental conditions, reduce operating costs, and identify energy savings opportunities, it is essential to efficiently manage energy consumption. Internet of Things (IoT) devices, including widely-used smart meters, have created possibilities for sensor based energy …
-
The Roles of Language Models and Hierarchical Models in Neural Sequence-to-Sequence Prediction
… in many areas of machine learning is converging towards the same set of methods and models. For example, long short-term memory networks are not only popular for various tasks in natural language processing (NLP) such as speech recognition, machine translation, handwriting recognition, syntactic …
-
Real-time Intrusion Detection using Multidimensional Sequence-to-Sequence Machine Learning and Adaptive Stream Processing
… as an intentional violation of the expected sequence of packets. In a real-time network-based IDS, incoming packets are treated as a stream of data. A stream processor takes any stream of data or events and extracts interesting patterns on the fly. This representation allows applying …
-
Reinforcement learning with natural language signals
… thesis we introduce a technique that allows one to use Natural Language as part of the state in Reinforcement Learning. We show that it is capable of solving Natural Language problems, similar to Sequence-to-Sequence models, but using multistage reasoning. We use Long Short-Term Memory Networks …
-
Data Augmentation with Seq2Seq Models
… corpus for the visual question answering system to make it more robust to paraphrases. This corpus is generated by concatenating two sequence to sequence models. In order to generate diverse paraphrases, we sample the neural network using diverse beam search. We evaluate the results on the …
-
Generalizable neural network representations of patient state in the intensive care unit
… Machine learning algorithms have been used to model patient physiology to predict patient outcomes and administration of interventions. These predictions can be made directly on the raw patient data extracted from electronic health records. However, this data can be high dimensional with …
-
Consonant (De)gradation in Ingrian?
<p>This paper will present a dual method toward data enrichment for low-resource languages. Using Yoyodyne -- a Fairseq-inspired neural library for small-vocabulary sequence-to-sequence generation -- a morphological generation task was tested across labeled data encompassing multiple stages of …
-
Uncertainty-aware learning from sparse, unlabelled, and out-of-distribution time series
… support improved diagnostics, personalised monitoring, and effective performance tracking. The ever-increasing availability of datasets from wearable sensors, mobile devices, and continuous monitoring technologies has created new opportunities for real-world applications, as they can offer a …
-
A Spam Transformer Model for SMS Spam Detection
… messages has become a serious problem. The need to block spam messages requires us to develop new SMS spam detection technologies. The Transformer, an attention- based sequence to sequence model, has achieved excellent results in multiple different tasks recently. In this thesis, we propose a …
-
Beatty: Automatic Tempo Curve Synthesis for Expressive MIDI Track Playback
Beatty is a sequence-to-sequence machine learning model to predict expressive timing decisions for excerpts of classical solo piano music. Composed of a bidirectional encoder LSTM and decoder LSTM with attention, Beatty predicts tempo labels based on input note sequences. The input note sequence is …
-
VirtualHome : learning to infer programs from synthetic videos of activities in the home
… that occur in a typical household. Programs - sequences of atomic actions and interactions - are used as a high-level, unambiguous representation of complex activities executable by an agent. However, no dataset of household activity programs currently exists. This project builds such a dataset …
-
Multi task learning and incorporating common sense knowledge for question answering
Question Answering (QA) system is an automated approach to retrieve correct responses to the questions asked by human in natural language. Reading comprehension (RC)in contrast to information retrieval, requires integrating information and reasoning about events, entities, and their relations …
-
Multi-fidelity Modeling and Reinforcement Learning for Energy Optimal Planning
Modeling the energy consumption of a quadrotor involves complex electrical and physical dynamics, making it difficult to optimize over. We present a sequence-to-sequence multi-fidelity Gaussian process (MFGP) to learn a data-driven model to predict the energy required to fly a given vehicle …
-
Definition modelling for English and Portuguese: a comparison between models and settings
… areas of knowledge; they convey meaning, refer to product conceptualization and naming, facilitate communication, provide clarity, and pervade all areas of human activity. Hence, having access to definitions is essential for many professions, but it is crucial for translation and interpreting. …
-
Universal approximation of input-output maps and dynamical systems by neural network architectures
… supported on a finite-dimensional compact set to arbitrary accuracy. However, many engineering applications require modeling infinite-dimensional functions, such as sequence-to-sequence transformations or input-output characteristics of systems of differential equations. For discrete-time …
-
Towards an end-to-end music transcription system using neural networks
… is the task of writing down instructions on how to play a particular piece of music, including individual notes, note durations, embellishments and so on. While most major works in the traditional repertoire have readily available transcriptions for various instrument arrangements, this is not as …
-
Formality Style Transfer Within and Across Languages with Limited Supervision
… When editing an article, professional editors take into account the target audience to select appropriate word choice and grammar. Similarly, professional translators translate documents for a specific audience and often ask what is the expected tone of the content when taking a …
-
Comparison between rule-based and data-driven natural language processing algorithms for Brazilian Portuguese speech synthesis
Due to the exponential growth in the use of computers, personal digital assistants and smartphones, the development of Text-to-Speech (TTS) systems have become highly demanded during the last years. An important part of these systems is the Text Analysis block, that converts the input text into …
-
Time-Optimal Re-planning of Quadrotor Trajectories
With the rise of quadrotor drones in recent years, the research and development of time-optimal trajectory planners are pushing the boundaries. They now not only exploit the full dynamics of the drone to generate aggressive trajectories but also have runtimes that allow them to generate plans in …
Page 1 of 3