NeurASP: Experiments and Evaluation - Part 3
Explore experimental evaluations of NeurASP, a neuro-symbolic framework connecting ASP programs to neural architectures, enabling end-to-end training through gradient passage.
Deep Ontological Networks: Introduction - Part 1
Explore Deep Ontological Networks with Prof. Simari, covering framework introduction, Semantic Web concepts, and ontology applications in AI and machine learning.
Visual Concept Grounding for Lifelong Learning
Explore visual concept grounding for lifelong learning with Yezhou Yang, delving into active perception and cutting-edge AI research at Arizona State University.
Machine Learning Integration with Knowledge Systems
Explore the intersection of symbolic methods and deep learning, focusing on integrating machine learning with knowledge-based approaches for advancing artificial intelligence.
Foundation Models and the Transfer of Embodied Autonomy
Explore challenges in developing foundation models for sequential decision-making, including transfer learning, and discuss future research directions in embodied autonomy.
Neuro-Symbolic AI and AllegroGraph 8.0: Revolutionizing Enterprise Knowledge Graphs
Explore AllegroGraph 8.0's revolutionary features in Enterprise Knowledge Graphs and Neuro-Symbolic AI. Learn how it integrates LLMs, Machine Learning, Symbolic AI, and Logic to enhance AI accuracy and reliability.
Deep Ontological Networks: Reasoning Process - Part 2
Explore deep ontological networks and reasoning processes with Professor Gerardo Simari. Dive into Datalog ontologies, RRN models, and GRUs for advanced AI understanding.
Introduction to Propositional Logic
Explore propositional logic fundamentals: atoms, operators, truth tables, natural language meaning, and inference rules for enhanced logical reasoning skills.
Trustworthy Decision Making in the Real World Through Uncertainty Reasoning
Explore trustworthy decision-making in real-world scenarios through uncertainty reasoning, focusing on metacognitive AI approaches and their practical applications.
An Architectural Approach to Metacognition - Metacognitive AI Series
Explore an architectural approach to metacognition in AI, focusing on integrating cognitive processes for enhanced machine reasoning and self-awareness.
Mutual Trust in Human-AI Teams Relies on Metacognition
Explore mutual trust in human-AI teams through metacognition. Gain insights into the role of metacognitive abilities in fostering collaboration between humans and artificial intelligence systems.
Assured Machine Learning: A Theoretically-Grounded Framework for High-Stakes Domains
Explore a theoretically-grounded framework for assured machine learning in high-stakes domains, focusing on the intersection of symbolic methods and deep learning.
Reasoning with Language Agents
Explore symbolic reasoning using language model agents in this talk by Prof. Swarat Chaudhuri. Gain insights into cutting-edge research at the intersection of AI and symbolic methods.
Probabilistic Circuits - Lecture on Advanced AI Techniques
Explore probabilistic circuits with YooJung Choi, delving into advanced AI concepts at the intersection of symbolic methods and deep learning.
Language Agents with LLMs - Evolutionary Step in Artificial Intelligence
Explore language agents as a critical evolutionary step in AI, focusing on LLM research and its implications for advancing artificial intelligence capabilities.
Scene Graphs: Overview and Current Research
Explore scene graphs and current research in this field, gaining insights into an exciting area of AI and machine learning.
Human-Aware Metacognitive AI - Lecture on Planning with Incomplete Model Knowledge
Explore human-aware planning and metacognitive AI with insights from Sarath Sreedharan, focusing on incomplete model-knowledge and AI-human interaction.
Introduction to Binarized Neural Networks
Explore binarized neural networks: motivation, quantization benefits, core concepts, training methods, and recent developments in this cutting-edge AI field.
Introduction to Symbol Grounding
Explore the symbol grounding problem, its philosophical roots, and major approaches including representationalist, semi-representationalist, and non-representationalist solutions.
Learning with Logical Constraints: Methods and Applications
Explore multiple methods for learning with logical constraints, including LTN, SPL, NASR, and STLNet. Gain insights into cutting-edge AI techniques combining symbolic methods and deep learning.
Logical Neural Networks: Unifying Statistical and Symbolic AI
Explore unifying statistical and symbolic AI through Logical Neural Networks, a framework combining neural networks with logical inference for improved knowledge representation and reasoning.