- About
-
The Global ETD Search service is a free service for researchers
to find electronic theses and dissertations. This service is
provided by the
Networked Digital Library of Theses and Dissertations.
Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
Search results
Showing 1 to 5 of 5 (0.032 seconds)Spelling suggestions: "subject:"neurosymbolic"" "subject:"neuralsymbolic""
| 1 |
End-to-End Neuro-Symbolic Approaches for Event RecognitionApriceno, Gianluca 30 October 2023 (has links)
Event detection is a critical challenge in many fields like video surveillance, social graph analysis, and multimedia processing. Furthermore, events are “structured” objects involv ing multiple components like the event type, the participants with their roles, and the atomic events in which it decomposes. Therefore, the recognition of an event is not only limited to recognize the type of the event and when it happened, but it involves solving a set of simple tasks. Exploiting background knowledge about events and their relations could then be beneficial for event detection. In the last years, neuro-symbolic integration has been proposed to merge the strengths and overcome the drawbacks of both symbolic and neural worlds. As a consequence, different neuro-symbolic frameworks, which com bine low-level perception of neural networks with a symbolic layer, encoding prior domain knowledge (usually defined in terms of logical rules), have been applied to solve different atemporal tasks. In this thesis, we want to investigate the application of the neuro-symbolic paradigm for event detection. This would also provide a better insight into the strengths and limitations of neuro-symbolic towards tasks involving time.
|
| 2 |
Can I open it? : Robot Affordance Inference using a Probabilistic Reasoning ApproachAguirregomezcorta Aina, Jorge January 2024 (has links)
Modern autonomous systems should be able to interact with their surroundings in a flexible yet safe manner. To guarantee this behavior, such systems must learn how to approach unseen entities in their environment through the inference of relationships between actions and objects, called affordances. This research project introduces a neuro-symbolic AI system capable of inferring affordances using attribute detection and knowledge representation as its core principles. The attribute detection module employs a visuo-lingual image captioning model to extract the key object attributes of a scene, while the cognitive knowledge module infers the affordances of those attributes using conditional probability. The practical capabilities of the neuro-symbolic AI system are assessed by implementing a simulated robot system that interacts within the problem space of jars and bottles. The neuro-symbolic AI system is evaluated through its caption-inferring capabilities using image captioning and machine translation metrics. The scores registered in the evaluation show a successful attribute captioning rate of more than 71%. The robot simulation is evaluated within a Unity virtual environment by interacting with 50 jars and bottles, equally divided between lifting and twisting affordances. The robot system successfully interacts with all the objects in the scene due to the robustness of the architecture but fails in the inference process 24 out of the 50 iterations. Contrary to previous works approaching the problem as a classification task, this study shows that affordance inference can be successfully implemented using a cognitive visuo-lingual method. The study’s results justify further study into the use of neuro-symbolic AI approaches to affordance inference.
|
| 3 |
Neural-Symbolic Modeling for Natural Language DiscourseMaria Leonor Pacheco Gonzales (12480663) 13 May 2022 (has links)
<p>Language “in the wild” is complex and ambiguous and relies on a shared understanding of the world for its interpretation. Most current natural language processing methods represent language by learning word co-occurrence patterns from massive amounts of linguistic data. This representation can be very powerful, but it is insufficient to capture the meaning behind written and spoken communication. </p>
<p> </p>
<p>In this dissertation, I will motivate neural-symbolic representations for dealing with these challenges. On the one hand, symbols have inherent explanatory power, and they can help us express contextual knowledge and enforce consistency across different decisions. On the other hand, neural networks allow us to learn expressive distributed representations and make sense of large amounts of linguistic data. I will introduce a holistic framework that covers all stages of the neural-symbolic pipeline: modeling, learning, inference, and its application for diverse discourse scenarios, such as analyzing online discussions, mining argumentative structures, and understanding public discourse at scale. I will show the advantages of neural-symbolic representations with respect to end-to-end neural approaches and traditional statistical relational learning methods.</p>
<p><br></p>
<p>In addition to this, I will demonstrate the advantages of neural-symbolic representations for learning in low-supervision settings, as well as their capabilities to decompose and explain high-level decision. Lastly, I will explore interactive protocols to help human experts in making sense of large repositories of textual data, and leverage neural-symbolic representations as the interface to inject expert human knowledge in the process of partitioning, classifying and organizing large language resources. </p>
|
| 4 |
Evaluation Functions in General Game PlayingMichulke, Daniel 24 July 2012 (has links) (PDF)
While in traditional computer game playing agents were designed solely for the purpose of playing one single game, General Game Playing is concerned with agents capable of playing classes of games. Given the game's rules and a few minutes time, the agent is supposed to play any game of the class and eventually win it.
Since the game is unknown beforehand, previously optimized data structures or human-provided features are not applicable. Instead, the agent must derive a strategy on its own.
One approach to obtain such a strategy is to analyze the game rules and create a state evaluation function that can be subsequently used to direct the agent to promising states in the match.
In this thesis we will discuss existing methods and present a general approach on how to construct such an evaluation function.
Each topic is discussed in a modular fashion and evaluated along the lines of quality and efficiency, resulting in a strong agent.
|
| 5 |
Evaluation Functions in General Game PlayingMichulke, Daniel 22 June 2012 (has links)
While in traditional computer game playing agents were designed solely for the purpose of playing one single game, General Game Playing is concerned with agents capable of playing classes of games. Given the game's rules and a few minutes time, the agent is supposed to play any game of the class and eventually win it.
Since the game is unknown beforehand, previously optimized data structures or human-provided features are not applicable. Instead, the agent must derive a strategy on its own.
One approach to obtain such a strategy is to analyze the game rules and create a state evaluation function that can be subsequently used to direct the agent to promising states in the match.
In this thesis we will discuss existing methods and present a general approach on how to construct such an evaluation function.
Each topic is discussed in a modular fashion and evaluated along the lines of quality and efficiency, resulting in a strong agent.:Introduction
Game Playing
Evaluation Functions I - Aggregation
Evaluation Functions II - Features
General Evaluation
Related Work
Discussion
|
Page generated in 0.0609 seconds