What do AI algorithms actually learn? - On false structures in deep learning

06/04/2019
by   Laura Thesing, et al.
0

There are two big unsolved mathematical questions in artificial intelligence (AI): (1) Why is deep learning so successful in classification problems and (2) why are neural nets based on deep learning at the same time universally unstable, where the instabilities make the networks vulnerable to adversarial attacks. We present a solution to these questions that can be summed up in two words; false structures. Indeed, deep learning does not learn the original structures that humans use when recognising images (cats have whiskers, paws, fur, pointy ears, etc), but rather different false structures that correlate with the original structure and hence yield the success. However, the false structure, unlike the original structure, is unstable. The false structure is simpler than the original structure, hence easier to learn with less data and the numerical algorithm used in the training will more easily converge to the neural network that captures the false structure. We formally define the concept of false structures and formulate the solution as a conjecture. Given that trained neural networks always are computed with approximations, this conjecture can only be established through a combination of theoretical and computational results similar to how one establishes a postulate in theoretical physics (e.g. the speed of light is constant). Establishing the conjecture fully will require a vast research program characterising the false structures. We provide the foundations for such a program establishing the existence of the false structures in practice. Finally, we discuss the far reaching consequences the existence of the false structures has on state-of-the-art AI and Smale's 18th problem.

READ FULL TEXT

page 2

page 9

page 10

research
09/13/2021

The mathematics of adversarial attacks in AI – Why deep learning is unstable despite the existence of stable neural networks

The unprecedented success of deep learning (DL) makes it unchallenged wh...
research
02/18/2022

On The "Majority is Least Stable" Conjecture

We show that the "majority is least stable" conjecture is true for n=1 a...
research
11/25/2021

Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks

Among the several paradigms of artificial intelligence (AI) or machine l...
research
01/31/2018

Deep Learning Works in Practice. But Does it Work in Theory?

Deep learning relies on a very specific kind of neural networks: those s...
research
06/04/2020

Characterizing the Weight Space for Different Learning Models

Deep Learning has become one of the primary research areas in developing...
research
03/23/2021

Any Part of Bayesian Network Structure Learning

We study an interesting and challenging problem, learning any part of a ...
research
06/02/2020

Recht-Ré Noncommutative Arithmetic-Geometric Mean Conjecture is False

Stochastic optimization algorithms have become indispensable in modern m...

Please sign up or login with your details

Forgot password? Click here to reset