Computational principles of intelligence: learning and reasoning with neural networks

Abstract

Despite significant achievements and current interest in machine learning and artificial intelligence, the quest for a theory of intelligence, allowing general and efficient problem solving, has done little progress. This work tries to contribute in this direction by proposing a novel framework of intelligence based on three principles. First, the generative and mirroring nature of learned representations of inputs. Second, a grounded, intrinsically motivated and iterative process for learning, problem solving and imagination. Third, an ad hoc tuning of the reasoning mechanism over causal compositional representations using inhibition rules. Together, those principles create a systems approach offering interpretability, continuous learning, common sense and more. This framework is being developed from the following perspectives: as a general problem solving method, as a human oriented tool and finally, as model of information processing in the brain.

References in corpus (8)

• Understanding deep learning requires rethinking generalization
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• Deep Learning: A Critical Appraisal
• One-Shot Visual Imitation Learning via Meta-Learning
• Distilling a Neural Network Into a Soft Decision Tree
• Regularization for Deep Learning: A Taxonomy
• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
• Action-Driven Object Detection with Top-Down Visual Attentions