Machine Learning Street Talk (MLST)

Francois Chollet - On the Measure of Intelligence


Listen Later

We cover Francois Chollet's recent paper.

Abstract; To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans. Over the past hundred years, there has been an abundance of attempts to define and measure intelligence, across both the fields of psychology and AI. We summarize and critically assess these definitions and evaluation approaches, while making apparent the two historical conceptions of intelligence that have implicitly guided them. We note that in practice, the contemporary AI community still gravitates towards benchmarking intelligence by comparing the skill exhibited by AIs and humans at specific tasks such as board games and video games. We argue that solely measuring skill at any given task falls short of measuring intelligence, because skill is heavily modulated by prior knowledge and experience: unlimited priors or unlimited training data allow experimenters to "buy" arbitrary levels of skills for a system, in a way that masks the system's own generalization power. We then articulate a new formal definition of intelligence based on Algorithmic Information Theory, describing intelligence as skill-acquisition efficiency and highlighting the concepts of scope, generalization difficulty, priors, and experience. Using this definition, we propose a set of guidelines for what a general AI benchmark should look like. Finally, we present a benchmark closely following these guidelines, the Abstraction and Reasoning Corpus (ARC), built upon an explicit set of priors designed to be as close as possible to innate human priors. We argue that ARC can be used to measure a human-like form of general fluid intelligence and that it enables fair general intelligence comparisons between AI systems and humans.

...more
View all episodesView all episodes
Download on the App Store

Machine Learning Street Talk (MLST)By Machine Learning Street Talk (MLST)

  • 4.7
  • 4.7
  • 4.7
  • 4.7
  • 4.7

4.7

84 ratings


More shows like Machine Learning Street Talk (MLST)

View all
Data Skeptic by Kyle Polich

Data Skeptic

481 Listeners

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) by Sam Charrington

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

440 Listeners

Super Data Science: ML & AI Podcast with Jon Krohn by Jon Krohn

Super Data Science: ML & AI Podcast with Jon Krohn

298 Listeners

NVIDIA AI Podcast by NVIDIA

NVIDIA AI Podcast

323 Listeners

Machine Learning Guide by OCDevel

Machine Learning Guide

765 Listeners

Practical AI by Practical AI LLC

Practical AI

189 Listeners

ManifoldOne by Steve Hsu

ManifoldOne

87 Listeners

Google DeepMind: The Podcast by Hannah Fry

Google DeepMind: The Podcast

199 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

372 Listeners

No Priors: Artificial Intelligence | Technology | Startups by Conviction

No Priors: Artificial Intelligence | Technology | Startups

122 Listeners

This Day in AI Podcast by Michael Sharkey, Chris Sharkey

This Day in AI Podcast

199 Listeners

Unsupervised Learning by by Redpoint Ventures

Unsupervised Learning

40 Listeners

Latent Space: The AI Engineer Podcast by swyx + Alessio

Latent Space: The AI Engineer Podcast

76 Listeners

The AI Daily Brief (Formerly The AI Breakdown): Artificial Intelligence News and Analysis by Nathaniel Whittemore

The AI Daily Brief (Formerly The AI Breakdown): Artificial Intelligence News and Analysis

441 Listeners

Training Data by Sequoia Capital

Training Data

36 Listeners