All current Computer Science Courses courses in 2024
3150 Cursussen
Safety of GenAI Through the Lens of Security and Cryptography
Immerse yourself in an enlightening session with Somesh Jha from the University of Wisconsin-Madison, focusing on the safety challenges faced by Generative AI. This course examines how security and cryptography frameworks can address safety concerns in AI development. Available exclusively on YouTube, it is a must-watch for enthusiasts of Arti.
Veridical Data Science Towards Trustworthy AI
Delve into the realm of veridical data science with esteemed expert Bin Yu from UC Berkeley. Discover how foundational principles of data science can be applied to develop trustworthy AI systems. Ideal for enthusiasts and professionals in Artificial Intelligence and Computer Science, this course offers valuable insights and knowledge to adva.
Provably Safe and Beneficial AI
Join us for an insightful exploration of Stuart Russell's groundbreaking approaches to constructing artificial intelligence systems. Discover the principles and methodologies for ensuring AI is not only advanced but also retains safety and significant benefits for humanity. Perfect for enthusiasts of Artificial Intelligence and Computer Scienc.
AI for Safety Critical Control
Explore the essential theoretical foundations of AI within safety-critical control systems in this insightful presentation by Claire Tomlin from UC Berkeley. This course emphasizes the importance of trust and reliability in environments where high-risk applications are managed using artificial intelligence.
Hosted on YouTube, this session is p.
Neurosymbolic Synthesis for Trustworthy Machine Learning
Discover how neurosymbolic synthesis can enhance the reliability and trustworthiness of machine learning applications. This session, led by Osbert Bastani from the University of Pennsylvania, provides valuable insights into the integration of symbolic reasoning and neural networks. Watch this comprehensive course on YouTube, ideal for enthusi.
Formal Models of Machine Teaching Without Collusion
Discover the key insights of formal models in machine teaching without the influence of collusion with Sandra Zilles, a renowned expert from the University of Regina. Engage with advanced concepts and theoretical perspectives on building trustworthy AI systems. Perfect for enthusiasts of artificial intelligence and computer science, this talk.
Trustworthy AI for Legal Reasoning
Delve into the innovative world of AI as it intersects with legal reasoning. Ruzica Piskac from Yale University takes you on a journey to understand how artificial intelligence can be applied to the realm of legal reasoning, with a keen focus on ensuring trustworthiness. This insightful session, presented at the Simons Institute and availa.
Towards Reasoning with a Million Environment Models
Explore sophisticated methods for reasoning with vast environment models in AI systems, emphasizing the theoretical aspects of trustworthy artificial intelligence. Join the University and YouTube collaboration to deepen your understanding of these cutting-edge techniques.
Categories: Artificial Intelligence Courses, Computer Science Courses
Theoretical Aspects of Trustworthy AI
Theoretical Aspects of Trustworthy AI by Susmit Jha
Explore the theoretical aspects of trustworthy AI in this insightful presentation by Susmit Jha from SRI International, a leading organization in technological innovations. Discover the key concepts and challenges that define the trustworthy AI landscape in this enlightening session. Avai.
Language Model Guided Synthesis for Lifting
Explore how the integration of language models with program synthesis paves the way for automating the lifting of code to domain-specific languages. This approach enhances the efficiency of code generation processes when working with heterogeneous hardware, offering advancements in the fields of artificial intelligence and computer science.
Synthesizing Pareto-optimal Interpretations of Black Box ML Models
Dive into the intricate process of synthesizing Pareto-optimal interpretations for black-box machine learning models. This course focuses on finding the perfect balance between the clarity of explainability metrics and the precision of model accuracy. Utilizing MaxSAT solving techniques, the content provides insights into achieving PAC-style.