RESEARCH

–

15 November 2022 0h22

Essentially every learning algorithm / inductive bias is applicable to this. E.g., think of learning a Bayes net where some of the variables are your actions. (How well it works is another question, and here causal theories are presumably very useful, but not exhaustive.)

→ View original post on X — @montreal_ai

15 November 2022

Evaluation Metrics for Language Modeling Explained

By

@montreal_ai

–

14 November 2022 23h24

Evaluation Metrics for Language Modeling https://
thegradient.pub/understanding-
evaluation-metrics-for-language-models/
…

→ View original post on X — @montreal_ai

Shannon’s Mathematical Theory of Communication Foundations

By

@montreal_ai

–

14 November 2022 23h14

A Mathematical Theory of Communication By C. E. SHANNON

Physics Laws as Master Algorithm: Intelligence Emergence

By

–

14 November 2022 22h22

The laws of physics are the master algorithm: run them long enough and intelligence emerges.

Inductive Bias, Complete Data, and Causal Theories Recap

By

–

14 November 2022 22h08

To recap:
– We always need prior assumptions/inductive biases, unless we have complete data (no free lunch theorem).
– If we have complete data, we don't need anything else for any rung.
– Causal theories are a type of inductive bias.
I guess that's a No answer to your question.

Complete Data Includes Mental States and Counterfactual Questions

By

–

14 November 2022 22h00

That's because the data is incomplete. Complete data includes the state of the actors' minds, and allows you to correctly answer counterfactual questions (which just correspond to different states of the world).

Incomplete Models: Action’s Role in Learning and Decision-Making

By

–

14 November 2022 21h43

Those models are incomplete, because they don't include your actions. Convergence aside, and tautologically, if you know everything there's nothing left to learn. You can then make optimal decisions without causal assumptions.

Priors and inductive biases are equivalent concepts

By

–

14 November 2022 21h38

Yes. (Again, priors and inductive biases are really the same thing.)

→ Voir le post original sur X — @rafiksmati

France strengthens mathematics to lead in AI and technology era

By

@rafiksmati

–

14 November 2022 20h07

Première journée des Assises des Mathématiques, à Paris. Les mathématiques sont à la racine de toutes les sciences et permettent de modéliser la complexité. Alors que nous entrons dans une ère hautement technologique, il est vital que la France revienne à l’avant-garde.