A Framework for Searching for General Artificial Intelligence

Abstract

There is a significant lack of unified approaches to building generally intelligent machines. The majority of current artificial intelligence research operates within a very narrow field of focus, frequently without considering the importance of the 'big picture'. In this document, we seek to describe and unify principles that guide the basis of our development of general artificial intelligence. These principles revolve around the idea that intelligence is a tool for searching for general solutions to problems. We define intelligence as the ability to acquire skills that narrow this search, diversify it and help steer it to more promising areas. We also provide suggestions for studying, measuring, and testing the various skills and abilities that a human-level intelligent machine needs to acquire. The document aims to be both implementation agnostic, and to provide an analytic, systematic, and scalable way to generate hypotheses that we believe are needed to meet the necessary conditions in the search for general artificial intelligence. We believe that such a framework is an important stepping stone for bringing together definitions, highlighting open problems, connecting researchers willing to collaborate, and for unifying the arguably most significant search of this century.

References in corpus (16)

• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Neural GPUs Learn Algorithms
• Convolutional Neural Fabrics
• Control of Memory, Active Perception, and Action in Minecraft
• Net2Net: Accelerating Learning via Knowledge Transfer
• AdaNet: Adaptive Structural Learning of Artificial Neural Networks
• Reinforcement Learning Neural Turing Machines - Revised
• Learning Functions: When Is Deep Better Than Shallow
• Learning Purposeful Behaviour in the Absence of Rewards
• Bounded Recursive Self-Improvement
• Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible
• Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
• Deep vs. shallow networks : An approximation theory perspective
• Learning dynamic Boltzmann machines with spike-timing dependent plasticity
• Why Artificial Intelligence Needs a Task Theory --- And What It Might Look Like
• Universal Psychometrics Tasks: difficulty, composition and decomposition

Cited by in corpus (3)

• ToyArchitecture: Unsupervised Learning of Interpretable Models of the World
• General AI Challenge - Round One: Gradual Learning
• Solving Tree Problems with Category Theory