Cognitive Architecture Requirements for Achieving AGI
نویسندگان
چکیده
We outline eight characteristics of the environments, tasks, and agents important for human-level intelligence. Treating these characteristics as influences on desired agent behavior, we then derive twelve requirements for general cognitive architectures. Cognitive-architecture designs that meet the requirements should support human-level behavior across a wide range of tasks, embedded in environment similar to the real world. Although requirements introduced here are hypothesized as necessary ones for human-level intelligence, our assumption is the list is not yet sufficient to guarantee the achievement of human-level intelligence when met. However, attempts to be explicit about influences and specific requirements may be more productive than direct comparison of architectural designs and features for communication and interaction about cognitive architectures.
منابع مشابه
A Foundational Architecture for Artificial General Intelligence
Implementing and fleshing out a number of psychological and neuroscience theories of cognition, the LIDA conceptual model aims at being a cognitive “theory of everything.” With modules or processes for perception, working memory, episodic memories, “consciousness,” procedural memory, action selection, perceptual learning, episodic learning, deliberation, volition, and non-routine problem solvin...
متن کاملThe LIDA Framework as a General Tool for AGI
Intelligent software agents aiming for general intelligence are likely to be exceedingly complex systems and, as such, will be difficult to implement and to customize. Frameworks have been applied successfully in large-scale software engineering applications. A framework constitutes the skeleton of the application, capturing its generic functionality. Frameworks are powerful as they promote cod...
متن کاملThe LIDA Model as a Foundational Architecture for AGI
Artificial intelligence (AI) initially aimed at creating “thinking machines,” that is, computer systems having human level general intelligence. However, AI research has until recently focused on creating intelligent, but highly domain-specific, systems. Currently, researchers are again undertaking the original challenge of creating AI systems (agents) capable of human-level intelligence, or “a...
متن کاملDeep Reinforcement Learning as Foundation for Artificial General Intelligence
Deep machine learning and reinforcement learning are two complementing fields within the study of intelligent systems. When combined, it is argued that they offer a promising path for achieving artificial general intelligence (AGI). This chapter outlines the concepts facilitating such merger of technologies and motivates a framework for building scalable intelligent machines. The prospect of ut...
متن کاملDesign of the Artificial: lessons from the biological roots of general intelligence
Our desire and fascination with intelligent machines dates back to the antiquity’s mythical automaton Talos, Aristotle’s mode of mechanical thought (syllogism) and Heron of Alexandria’s mechanical machines and automata. However, the quest for Artificial General Intelligence (AGI) is troubled with repeated failures of strategies and approaches throughout the history. This decade has seen a shift...
متن کامل