--The AI system GPT-2, in a December 2019 interview with The Economist, "An artificial intelligence predicts the future" Innateness, empiricism, and recent developments in deep learning Consider two classic hypotheses about the development of language and cognition.
There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values.
Generative vs Contrastive Methods Contemporary self-supervised learning methods can roughly be broken down into two classes of methods: Loss measured in the output space Examples: Colorization, Auto-Encoders Loss measured in the representation space Examples: TCN, CPC, Deep-InfoMax
Polygames’ architecture makes it compatible with more kinds of games — including Breakthrough, Hex, Havannah, Minishogi, Connect6, Minesweeper, Mastermind, EinStein würfelt nicht!, Nogo, and Othello — than previous systems, such as AlphaZero and ELF OpenGo.
Today, Dr. Gao gives us an overview of the deep learning landscape and talks about his latest work on Multi-task Deep Neural Networks, Unified Language Modeling and vision-language pre-training.