Episode 91: The Critical Rationalist Case For Induction!?

9 snips

Aug 20, 2024

The discussion centers around Popper's critical analysis of induction, framing it as nonexistent. It delves into the philosophical debates contrasting good and bad explanations, featuring the intersection of Popper's ideas and modern machine learning. The speakers highlight the importance of empirical testability and explore the relevance of induction in scientific reasoning. Themes of creativity in AI and the complexities of hypothesis formation also emerge, showcasing the interplay between critical rationalism and contemporary practices.

Ask episode

Chapters

Transcript

Episode notes

Intro

00:00 • 2min

The Dynamics of Theoretical Evolution: Understanding Popper's Ratchet

02:13 • 4min

The Induction Debate in Science

06:31 • 34min

Enhancing Hypotheses in Sports and Weather Analysis

40:24 • 7min

Candidate Elimination Algorithm Explained

47:03 • 9min

Inductive Bias and Machine Learning

56:22 • 26min

Exploring the Intersection of Creativity and Machine Learning

01:22:08 • 2min

The Complexity of Induction

01:24:35 • 21min

Forgive the clickbait title. The episode should probably actually be called "The (Lack of) Problem of Induction" because we primarily cover Popper's refutation of induction in C&R Chapter 8.

This episode starts our deep dive into answering the question "What is the difference between a good philosophical explanation and a bad explanation?"

To answer that question we go over Karl Popper's "On the Status of Science and of Metaphysics" from his book Conjectures and Refutations Chapter 8. In this chapter Popper first explains why he believes 'there is no such thing as induction' (from page 18 of Logic of Scientific Discovery) by offering his historical and logical refutation of induction.

In this episode we go over Popper's refutation of induction in chapter 8 of C&R in detail and then compare it to Tom Mitchell's (of Machine Learning fame) argument of the 'futility of bias free learning.' We show that Mitchell's and Popper's arguments are actually the same argument even though Mitchell argues for the existence of a kind of induction as used in machine learning.

Bruce argues that the difference is not a conceptual or theoretical difference but just a difference in use of language and that the two men are actually conceptually fully in agreement. This makes machine learning both a kind of 'induction' (though not the kind Popper refuted) and also gives machine learning an interesting and often missed relationship with critical rationalism.

Then Bruce asks the most difficult question of all: "Is there anyone out there in the world other than me that is interested in exploring how to apply Karl Popper's epistemology to machine learning like this?"

You can find a copy of Mitchell's text here if you want to check out his argument for the futility of bias free learning for yourself.

As I mention in the podcast, I'm shocked Critical Rationalists aren't referencing Mitchell's argument constantly because it is so strongly critical rationalist in nature. But the whole textbook is just like this.