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 693 for “"Multi-task"”.
-
Multi-task generalization for robotics
… that can autonomously accomplish different tasks in unstructured environments with unforeseen variations remains a key challenge. Inspired by the recent success of foundation models in different domains, robotic learning has been going through a paradigm shift from learning specialist robots …
-
Massively parallelized multi-task reinforcement learning
Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy. However, online MTRL has largely been limited to training policies using …
-
On Kernel-base Multi-Task Learning
Multi-Task Learning (MTL) has been an active research area in machine learning for two decades. By training multiple relevant tasks simultaneously with information shared across tasks, it is possible to improve the generalization performance of each task, compared to training each individual task …
-
Multi-Task Averaging: Theory and Practice
… addresses the problem of estimating the means of multiple distributions. I begin with a brief history of the mean, leading to a discussion and literature review of Stein estimation and multi-task learning. Using a multi-task regularized empirical risk formulation, an algorithm called multi-task …
-
Multi-task learning for hate speech detection
… we propose framing hate speech detection as multi-task learning (MTL) which provides a natural and principled way for a model to specialize on dataset-specific hate speech detection tasks while leveraging shared notions of hate speech across datasets to acquire more general notions of hate …
-
Switch choice in applied multi-task management
… cognitive load is high and they are faced with multiple different tasks to choose from. This dissertation reviewed a large body of voluntary task switching literature concerning basic research into choice in task switching, as well as what literature was available for applied task switching. …
-
Processing questions with multi-task sentence embedding
… of text, researchers created various tasks to train the algorithms and language models. The machine was trained to understand articles, emails, and even shorter text like Tweets. With the development of online questioning communities and voice assistants, we notice a new type of text …
-
Multi-Task Neural Networks for Speech Recognition
První část této diplomové práci se zabývá teoretickým rozborem principů neuronových sítí, včetně možnosti jejich použití v oblasti rozpoznávání řeči. Práce pokračuje popisem viceúkolových neuronových sítí a souvisejících experimentů. Praktická část práce obsahovala změny software pro trénování …
-
Towards Improving Generalization of Multi-Task Learning
Multi-task Learning (MTL), which involves the simultaneous learning of multiple tasks, can achieve better performance than learning each task independently. It has achieved great success in various applications, ranging from computer vision to bioinformatics. However, involving multiple tasks in a …
-
Preventive Maintenance for a Multi-task System
This research models the behavior of a multi-task system with respect to time. The type of multi-task system considered here is one in which not all system components are required to perform each task. Each component may, however, be used for more than one task. Also, it is possible that some of …
-
IMPROVING INFORMATION EXTRACTION WITH WEIGHTED MULTI-TASK LEARNING
Information extraction is a challenging task that extracts structured information from unstructured text. Traditional machine learning techniques for information extraction require task-specific training data and manually engineered features, many of which require a pipeline of external sub-systems …
-
Communcation-efficient algorithms for decentralized multi-task learning
… yet full synchronization scales poorly. When multiple nodes collaborate through pairwise regularizers, standard methods require a number of communications proportional to the total number of regularizers per iteration. We propose randomized local coordination, in which each node independently …
-
A minimalist approach to deep multi-task learning
<p>Multi-task learning is critical for real-life applications of machine learning. Modern approaches are characterised by algorithmic complexity, often unjustified, leading to impractical solutions. In contrast, this thesis demonstrates that a minimalistic alternative is possible, showing the …
-
MTSS: Multi Task Stack Sharing For Embedded Systems
… estimation. This work improves reliability for multi-tasking embedded systems by proposing MTSS, a multi-task stack sharing technique, that grows the stack of a particular task into other tasks in the system if the task attempts to overflow its bounds. This technique can avoid the out-of-memory …
-
Task Generalized MDPs for Multi-Task Reinforcement Learning
… reasons for this inefficiency is that every new task is usually learned from scratch, instead of leveraging information from similar tasks. In this talk, I will describe task-generalized Markov Decision Processes which are built from a distribution of tasks, or MDPs that differ only in their …
-
The power of adaptivity in multi-task representation learning
Learning models that perform well across multiple tasks or clients simultaneously are desired in robotics, edge computing, and increasingly many machine learning and artificial intelligence applications. Often in these settings, there are many tasks available for training models, although the …
-
Towards Understanding Conflict & Transfer in Multi-Task Deep Learning
Multi-task learning (MTL)-training a model to fit multiple tasks or distributions simultaneously-has become a cornerstone in the training of foundation models such as large language models (LLMs). However, despite it's widespread adoption, multi-task learning often leads to negative transfer, …
-
DEEP MULTI-TASK LEARNING FOR FACE AND HUMAN ANALYSIS
In this thesis, we use multi-task learning methods to solve face and human analysis tasks. We design multi-task learning models to learn multiple face and human analysis tasks. We demonstrate that deep multi-task learning can be used to perform the face attribute classification task and up to 40 …
Page 1 of 35