# Induction, Popper, and machine learning

arXiv: https://arxiv.org/abs/2110.00840 · HTML: https://mlsanity.com/paper/2110.00840/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 2 Oct 2021.

## Builds on (most cited first, 7 of 7)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [The Loss Surfaces of Multilayer Networks](https://mlsanity.com/paper/1412.0233/) (2014)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Embedded Agency](https://mlsanity.com/paper/1902.09469/) (2019)
- [Holes in Bayesian Statistics](https://mlsanity.com/paper/2002.06467/) (2020)
- [Applying Deutsch's concept of good explanations to artificial intelligence and neuroscience -- an initial exploration](https://mlsanity.com/paper/2012.09318/) (2020)

## Built on by (most cited first, 1 of 1)

- [Inductive Models for Artificial Intelligence Systems are Insufficient without Good Explanations](https://mlsanity.com/paper/2401.09011/) (2024)

## Abstract (arXiv)

Francis Bacon popularized the idea that science is based on a process of induction by which repeated observations are, in some unspecified way, generalized to theories based on the assumption that the future resembles the past. This idea was criticized by Hume and others as untenable leading to the famous problem of induction. It wasn't until the work of Karl Popper that this problem was solved, by demonstrating that induction is not the basis for science and that the development of scientific knowledge is instead based on the same principles as biological evolution. Today, machine learning is also taught as being rooted in induction from big data. Solomonoff induction implemented in an idealized Bayesian agent (Hutter's AIXI) is widely discussed and touted as a framework for understanding AI algorithms, even though real-world attempts to implement something like AIXI immediately encounter fatal problems. In this paper, we contrast frameworks based on induction with Donald T. Campbell's universal Darwinism. We show that most AI algorithms in use today can be understood as using an evolutionary trial and error process searching over a solution space. In this work we argue that a universal Darwinian framework provides a better foundation for understanding AI systems. Moreover, at a more meta level the process of development of all AI algorithms can be understood under the framework of universal Darwinism.