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 22 for “"End-to-End Learning"”.
-
Robust end-to-end learning for autonomous vehicles
Deep learning has been successfully applied to "end-to-end" learning of the autonomous driving task, where a deep neural network learns to predict steering control commands from camera data input. While these works support reactionary control, the representation learned is not usable for …
-
End-to-end Learning for Robust Decision Making
… is complex, ambiguous, and unpredictable, autonomous agents must be engineered to exhibit a human-level degree of flexibility and generality — far beyond what we are capable of explicitly programming. Such realizations of autonomy are capable of not only reliably solving a particular problem, …
-
Reinforcement Learning with a Lost Person Model for Search and Rescue Path Planning
In this thesis, we train a reinforcement learning agent to plan paths for search and rescue applications using a model of lost person behavior trained on past search incidents. We propose an improved method for producing occupancy maps from the trajectories of an agent-based lost person model. We …
-
On the computational power of RNNs
… Recurrent Unit (GRU) have gained prominence as end-to-end learning architectures for natural language processing tasks. But what is the computational power of such systems? We prove that finite precision RNNs with one hidden layer and ReLU activation and finite precision GRUs are exactly as …
-
Neural Voice Activity Detection and its practical use
The task of producing a Voice Activity Detector (VAD) that is robust in the presence of non-stationary background noise has been an active area of research for several decades. Historically, many of the proposed VAD models have been highly heuristic in nature. More recently, however, statistical …
-
Stubborn: A Strong Baseline for the Indoor Object Navigation Task
… a widely-studied task that requires the agent to navigate to an instance of a given object category in unseen indoor environments. Previous state-of-the-art methods to this task include mapfree end-to-end learning-based methods and methods that maintain and plan with spatial maps, but they both …
-
Robust Dexterous Manipulation Enabled by Learning at Scale inSimulation
… robust bimanual dexterity have the potential to transform industries such as manufacturing and healthcare by performing complex tasks at human-level proficiency. While end-to-end learning methods have shown promise in achieving this goal, scaling these approaches remains challenging. Existing …
-
Robot learning with strong priors
Embedding learning ability in robotic systems is one of the long sought-after objectives of artificial intelligence research. Despite the recent advancements in hardware, large-scale machine learning algorithms and theoretical understanding of deep learning, it is still quite unrealistic to deploy …
-
A Graph Convolutional Neural Network Based Approach for Object Tracking Using Augmented Detections With Optical Flow
… Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to …
-
Aligning Machine Learning and Robust Decision-Making
Machine learning (ML) has become increasingly ubiquitous across many applications worldwide, ranging from areas like supply chain to personalized pricing, recommendations, and more. These predictive models are often used as tools to inform operations and decision-making, with the potential to …
-
Non-linguistic Notions in Language Modeling: Learning, Retention, and Applications
… and use artificial intelligence (AI) and machine learning (ML) in our daily lives. Although LLMs have showcased remarkable linguistic proficiency in their abilities to write, summarize, and phrase, these model have yet to achieve the same remarkability in their ability to quantitatively reason. …
-
Deep learning for automatic microscopy image analysis
… Manual MIA is tedious, time-consuming, prone to subject errors, and are not feasible for the high-throughput cell analysis process. Thus, automatic MIA methods can facilitate all kinds of biological studies and clinical tasks. Conventional feature engineering-based methods use handcrafted …
-
SCALABLE MATCHING OF DEFORMED IMAGES
… is a fundamental inverse problem ubiquitous across biomedical and life science applications. Over the past three decades, advances in imaging technology have democratized access to unprecedented spatial and temporal detail, while an equally staggering growth in GPU hardware has …
-
Physics-Aware Optimization and Data-Driven Methods for Low-Carbon Power Systems
The US electricity sector is undergoing a transformation with aggressive targets to achieve 100% carbon pollution-free electricity by 2035. To achieve this objective while maintaining a safe and reliable power grid in the presence of intermittent renewable generation, new operating paradigms of …
-
Recurrent Neural Network Language Generation for Dialogue Systems
… is the most natural and effective way for humans to interact with and access information from machines. Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact on usability and perceived quality. Many commonly used NLG systems employ rules and …
-
Bilevel Optimization in the Deep Learning Era: Methods and Applications
… of neural networks lies in their capability to autonomously learn intricate representations that map input data to corresponding output labels seamlessly. Nevertheless, not all tasks can be neatly encapsulated within the confines of an end-to-end learning paradigm. The complexity and …
-
BEYOND LOCAL NEIGHBORHOODS: LEVERAGING INFORMATIVE NODES FOR IMPROVED GRAPH NEURAL NETWORKS PERFORMANCE
… as nodes and their relationships as edges. To analyze the properties of individual entities (node classification) or the community as a whole (graph classification), graph neural networks (GNNs) serve as a powerful tool. Most GNNs utilize a message-passing scheme to aggregate information …
-
Prognostics and health management for multi-component systems
… pushing original equipment manufacturers (OEM) to design more complex systems to meet industrial needs. These systems are being fitted with more components which bear stochastic and economic dependencies. Therefore maintaining such systems is becoming more and more of a challenge, especially due …
-
Characterization of Structure-Borne Tire Noise Using Virtual Sensing
Various improvements which have been made to the vehicle (reduced engine noise, reducedaerodynamic related NVH), have resulted in tire road noise as the dominant source of thevehicle interior noise. Generally, vehicle interior noise has two main sources, 1) travellinglow frequency excitation below …
-
Graph Neural Networks for Multi-Robot Coordination
… particularly interested in investigating machine learning (especially graph neural network) based approaches to find the trade-off between optimality and complexity by offloading online computation into an offline training process. Yet, learning-based methods also yield the need for sim-to-real …
Page 1 of 2