Bridging the Gap between Artificial Intelligence and Artificial General Intelligence: A Ten Commandment Framework for Human-Like Intelligence
Not on the map. Why?
Abstract (arXiv)
The field of artificial intelligence has seen explosive growth and exponential success. The last phase of development showcased deep learnings ability to solve a variety of difficult problems across a multitude of domains. Many of these networks met and exceeded human benchmarks by becoming experts in the domains in which they are trained. Though the successes of artificial intelligence have begun to overshadow its failures, there is still much that separates current artificial intelligence tools from becoming the exceptional general learners that humans are. In this paper, we identify the ten commandments upon which human intelligence is systematically and hierarchically built. We believe these commandments work collectively to serve as the essential ingredients that lead to the emergence of higher-order cognition and intelligence. This paper discusses a computational framework that could house these ten commandments and suggests new architectural modifications that could lead to the development of smarter, more explainable, and generalizable artificial systems inspired by a neuromorphic approach.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 87 references that are in the map. First posted on arXiv 17 Oct 2022.
Builds on
29 of 87 references.
References · 29
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
- 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
- 2020Shortcut Learning in Deep Neural Networkscited by 1,969
- 2021ViViT: A Video Vision Transformercited by 1,620
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
- 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
- 2020Beyond English-Centric Multilingual Machine Translationcited by 561
- 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
- 2017Deep Reinforcement Learning: An Overviewcited by 333
- 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
- 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
17 more
- 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 258
- 2021Mastering Atari Games with Limited Datacited by 237
- 2017The Consciousness Priorcited by 107
- 2017Building machines that adapt and compute like brainscited by 99
- 2019How Can We Be So Dense? The Benefits of Using Highly Sparse Representationscited by 45
- 2017Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Datacited by 33
- 2020DeepAbstract: Neural Network Abstraction for Accelerating Verificationcited by 31
- 2019Enabling real-time multi-messenger astrophysics discoveries with deep learningcited by 18
- 2016Supervision via Competition: Robot Adversaries for Learning Taskscited by 16
- 2021Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networkscited by 15
- 2016How do neurons operate on sparse distributed representations? A mathematical theory of sparsity, neurons and active dendritescited by 14
- 2020Batch Exploration with Examples for Scalable Robotic Reinforcement Learningcited by 14
- 2019Deep learning and face recognition: the state of the artcited by 11
- 2019Neural Mechanisms of Human Decision-Makingcited by 5
- 2021Complementary Structure-Learning Neural Networks for Relational Reasoningcited by 3
- 2018State-Denoised Recurrent Neural Networkscited by 1
- 2021A Mathematical Approach to Constraining Neural Abstraction and the Mechanisms Needed to Scale to Higher-Order Cognitioncited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.