A New Framework for Machine Intelligence: Concepts and Prototype
arXiv:1806.02137
Abstract
Machine learning (ML) and artificial intelligence (AI) have become hot topics in many information processing areas, from chatbots to scientific data analysis. At the same time, there is uncertainty about the possibility of extending predominant ML technologies to become general solutions with continuous learning capabilities. Here, a simple, yet comprehensive, theoretical framework for intelligent systems is presented. A combination of Mirror Compositional Representations (MCR) and a Solution-Critic Loop (SCL) is proposed as a generic approach for different types of problems. A prototype implementation is presented for document comparison using English Wikipedia corpus.
References in corpus (13)
- Overcoming catastrophic forgetting in neural networks
- Neural Discrete Representation Learning
- Self-Attention Generative Adversarial Networks
- Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
- Deep Learning: A Critical Appraisal
- Distilling a Neural Network Into a Soft Decision Tree
- Document Embedding with Paragraph Vectors
- Data-Efficient Hierarchical Reinforcement Learning
- Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
- Learning Visual Predictive Models of Physics for Playing Billiards
- Dynamic Routing Between Capsules
- Visual Interpretability for Deep Learning: a Survey
- Action-Driven Object Detection with Top-Down Visual Attentions