Three problems in computer science

By Leslie G. Valiant. 2003

69 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, background): “In this respect, Turing Award Winner Leslie Valiant had already pointed out that one of the key challenges for AI in the coming decades is the development of integrated reasoning and learning mechanisms, so as to construct a rich semantics of intelligent cognitive behavior [54].”
Dimensions of Neural-symbolic Integration - A Structured Survey (2005, background): “Ultimately, our goal should be to produce an effective AI system with added reasoning and learning capabilities, as recently pointed out by Valiant [Valiant, 2003] as a key challenge for computer science.”
A Connectionist Computational Model for Epistemic and Temporal Reasoning (2006, methodology): “(Valiant, 2003) Taking the requirements put forward by Valiant into consideration, this article provides a robust connectionist computational model for epistemic and temporal reasoning.”
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation (2017, methodology): “…how to reconcile the statistical nature of learning with the logical nature of reasoning, aiming to build such robust computational models integrating concept acquisition and manipulation, has been identified as a key research challenge and fundamental problem in computer science (Valiant, 2003).”
Learning and Representing Temporal Knowledge in Recurrent Networks (2011, unknown): “The results illustrate how model verification and learning can be integrated within a neural computation paradigm, and indicate that the integration of methodologies from symbolic AI and connectionism is relevant for building robust and sound intelligent systems [1], [3], [6].”
Explainable AI (XAI): Core Ideas, Techniques, and Solutions (2022, background): “What we can infer from contemporary works is that the combination of neural and symbolic approaches brings together “two most fundamental aspects of intelligent cognitive behavior: the ability to learn from experience and the ability to reason from what was learned” [59].”
Logic Tensor Networks (2020, background): “Artificial Intelligence (AI) agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions, act in the world or react to various stimuli [68].”
A Connectionist Cognitive Model for Temporal Synchronisation and Learning (2007, methodology): “The construction of rich computational cognitive models has recently been pointed out as a key research question for computer science and cognitive computation (Valiant 2003).”
Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks (2018, unknown): “…representations have been deployed successfully in many intelligent and multiagent systems, ﬂexible representations and forms of reasoning are needed that can account for the inherent uncertainty in the problems tackled by AI [1], [2], such as, for example, handling noise in video and audio data.”
Neurosymbolic AI: the 3rd wave (2020, background): “Here, however, we have been discussing the science of what constitutes the fundamental ingredients of an intelligent system (Valiant 2003).”