1 |
Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Testing Low-Frequency Neural Activity in Sentence Understanding
|
|
|
|
BASE
|
|
Show details
|
|
3 |
The Syntax, Semantics and Processing of Agreement and Binding Grammatical Illusions
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Using Eye-tracking to Examine Grammatical Predictability in Spanish-English Bilinguals and Spanish Language Learners
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Retrieval Interference in Syntactic Processing: The Case of Reflexive Binding in English
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Retrieval Interference in Syntactic Processing: The Case of Reflexive Binding in English
|
|
|
|
BASE
|
|
Show details
|
|
8 |
From Verbs to Tasks: An Integrated Account of Learning Tasks from Situated Interactive Instruction.
|
|
|
|
BASE
|
|
Show details
|
|
9 |
The Contrast-dependent CI-Calculation of Topic and Focus in Korean Transitive Constructions.
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Computational Rationality: Linking Mechanism and Behavior Through Bounded Utility Maximization
|
|
|
|
BASE
|
|
Show details
|
|
13 |
The Adaptive Nature of Eye Movements in Linguistic Tasks: How Payoff and Architecture Shape Speed‐Accuracy Trade‐Offs
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Effective and Efficient Memory for Generally Intelligent Agents.
|
|
|
|
Abstract:
Intelligent systems with access to large stores of experience, or memory, can draw upon and reason about this knowledge in a variety of situations, such as to improve the efficacy of their learning, decision-making, and actions in the world. However, little research has examined the computational challenges that arise when real-time agents require access to large stores of knowledge over long periods of time. This dissertation explores the computational trade-offs involved in enhancing intelligent agents with effective and efficient memory. We exploit general properties of environments, tasks, and agent cues in order to develop scalable algorithms for episodic learning (autobiographical memory); semantic learning (context-independent store of facts and relations); and competence-preserving retention of learned knowledge (policies to forget memories while maintaining task performance). We evaluate these algorithms in Soar, a general cognitive architecture, for hours-to-days of real-time execution and demonstrate that agents with effective and efficient memory benefit along numerous dimensions when tasked within a variety of problem domains, including linguistics, planning, games, and mobile robotics.
|
|
Keyword:
Artificial Intelligence; Cognitive Architecture; Episodic Memory; Forgetting; Semantic Memory; Soar
|
|
URL: http://hdl.handle.net/2027.42/93855
|
|
BASE
|
|
Hide details
|
|
17 |
Short-term Memory Retrievals and Expectation in On-line Sentence Comprehension: The Effects of Recent Linguistic Context.
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Root, Successive-Cyclic and Feature-Splitting Internal Merge: Implications for Feature-Inheritance and Transfer.
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Processing Coordinated Verb Phrases: The Relevance of Lexical-Semantic, Conceptual, and Contextual Information towards Establishing Verbal Parallelism.
|
|
|
|
BASE
|
|
Show details
|
|
|
|