The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
arXiv:2002.06177
Abstract
Recent research in artificial intelligence and machine learning has largely emphasized general-purpose learning and ever-larger training sets and more and more compute. In contrast, I propose a hybrid, knowledge-driven, reasoning-based approach, centered around cognitive models, that could provide the substrate for a richer, more robust AI than is currently possible.
5 figures
References in corpus (16)
- Solving Rubik's Cube with a Robot Hand
- Large-scale Simple Question Answering with Memory Networks
- Deep Learning: A Critical Appraisal
- Adversarial Examples for Evaluating Reading Comprehension Systems
- Towards a Human-like Open-Domain Chatbot
- MONet: Unsupervised Scene Decomposition and Representation
- Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
- Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
- A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
- Frequently Asked Questions for: The Atoms of Neural Computation
- Environmental drivers of systematicity and generalization in a situated agent
- Deep Learning for Symbolic Mathematics
- Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
- Learning Symbolic Physics with Graph Networks
- The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)
- Learning dynamic polynomial proofs