Computers could understand natural language using simulated physics
Image courtesy of Barking Dog http://u3d.as/sUNComputers currently understand us by mapping what we say to symbols or vectors and then performing inference based on those data structures. As I argued...
View ArticleYou and Your Bot: A New Kind of Lifelong Relationship
In my last blog post, I discussed how computers could understand natural language by simulating our world. Such an understanding would enable us to build a bot that could be our lifelong teacher,...
View ArticleChatbots: Theory and Practice
There’s a lot of fluff surrounding chatbots, so I wrote this post to lay out the basics. I first review the theory of conversation to give us a sense of what we are aiming for. I then discuss three...
View ArticleWhy is there life? And what does it have to do with AI?
Dust devil in Mongolia. By Texasbob (Own work) [CC BY-SA 3.0 (https://creativecommons.org/licenses/by-sa/3.0)], via Wikimedia CommonsI love when my old questions get answered. Twenty years ago, I lay...
View ArticleGenerating Natural-Language Text with Neural Networks
Computers are illiterate. Reading requires mapping the words on a page to shared concepts in our culture and commonsense understanding, and writing requires mapping those shared concepts into other...
View ArticleMicrosoft Flight Simulator 2020 is an inflection point for virtual worlds and...
Flying into Austin from the East on my son’s underpowered Windows computer.Microsoft Flight Simulator (MSFS) 2020 doesn’t just feel real; it almost is real. You see the same objects and relationships...
View ArticleThe Two Paths from Natural Language Processing to Artificial Intelligence
Why isn’t Siri smarter? AI has accelerated in recent years, especially with deep learning, but current chatbots are an embarrassment. Computers still can’t read or converse intelligently. Their...
View ArticleIntroducing ThoughtLog: The Free Automatic Diary
Our thoughts are our experience in this world, and our worries, memories, and plans are the only real testimony to our existence. Moment by moment, it feels like we are thinking about what’s naturally...
View ArticleRLlib for Deep Hierarchical Multiagent Reinforcement Learning
Reinforcement learning (RL) is an effective method for solving problems that require agents to learn the best way to act in complex environments. RLlib is a powerful tool for applying reinforcement...
View Article
More Pages to Explore .....