|||

At AI SF, Danny Lange presented how to train puppies: On the road to artificial general intelligence” — game simulations Unity3D plus reinforcement learning used to train virtual puppies to play fetch” and other skills. Building on this, Danny described several forms of learning inspired by biology, which go beyond deep learning. He showed examples of virtual puppies for:

Imitation Learning: e.g., see https://bit.ly/2zvYH51 (start 0:15)
Curriculum Learning: start with an easy problem, then make learning challenges progressively harder
Curiosity-driven Exploration: gets beyond problems which random exploration would never reach, i.e., agents don’t get stuck in a room (saddle points) because they want to explore other rooms

https://blog.dominodatalab.com/themes-and-conferences-per-pacoid-episode-2/
Up Next Next → These days with fast commodity networking, the economics of cloud services don’t resemble “commodity servers” circa early Hadoop at all https://blog.dominodatalab.com/themes-and-conferences-per-pacoid-episode-2/ ← Previous Check out her Altimeter Group white paper, “The Customer Experience of AI: Five Principles to Foster Engagement, Innovation and Trust” https://blog.dominodatalab.com/themes-and-conferences-per-pacoid-episode-2/
Latest posts
▵  Twitter announces Bluesky: a team seeking and developing an open standard for social media
▵  Elon Musk attempts to explain Twitter to normal people in court
▵  TED and YouTube launch global climate initiative
▵  Embracing multilingualism to enhance complexity sensitive research
▵  The ‘Amazon effect’ is flooding a struggling recycling system with cardboard
▵  John Kerry, Arnold Schwarzenegger wage ‘World War Zero’ on climate change
▵  Combining semantic and term frequency similarities for text clustering
▵  Bad RCS implementations are creating big vulnerabilities, security researchers claim
▵  2019 Tech Trends Report — The Future Today Institute
▵  Medical Crowdsourcing: Harnessing the “Wisdom of the Crowd” to Solve Medical Mysteries
▵  Report Launch - OPSI Primer on AI for the Public Sector
▵  “Level Up”: Leveraging Skill and Engagement to Maximize Player Gameplay
▵  Beautiful is Good and Good is Reputable: Multiple-Attribute Charity Website Evaluation and Initial Perceptions of Reputation Under the Halo Effect
▵  Piret Tõnurist & Systems Change: how to get started and keep going?
▵  IBM expert Tamreem El Tohamy on bridging the skills gap in Africa
▵  The changing work of innovation for public value and social impact
▵  Former Go champion beaten by DeepMind retires after declaring AI invincible
▵  What part of “viral” content makes platforms want to encourage its spread?
▵  MTA floods NYC subway entrance because ‘climate change is real’
▵  The Demon Haunted World
▵  How to recognize AI snake oil
▵  A Systemic View of Research Impact
▵  Nobel Economics Prize Goes to Pioneers in Reducing Poverty
A brief, informal guide to doing grounded theory
▵  Adam Savage on Lists, More Lists, and the Power of Checkboxes
▵  Systems Practice, Abridged
▵  Fukushima reinvents itself with a $2.7 billion bet on renewables
▵  How Tesla’s first Gigafactory is changing Reno, Nevada
▵  “This is Sticking with Them:” Professor Explores Benefits of Model-Based Learning
Keeping the buzz in buzzwords
▵  README.txt: Introducing Into the Dataverse, the article series