papers

Publications (9)

cs.LG2022

Quantifying Local Specialization in Deep Neural Networks

Shlomi Hod, Daniel Filan, Stephen Casper +2

A neural network is locally specialized to the extent that parts of its computational graph (i.e. structure) can be abstractly represented as performing some comprehensible sub-tas…

cs.NE2021

Clusterability in Neural Networks

Daniel Filan, Stephen Casper, Shlomi Hod +3

The learned weights of a neural network have often been considered devoid of scrutable internal structure. In this paper, however, we look for structure in the form of clusterabili…

cs.LG2025

Constrained belief updates explain geometric structures in transformer representations

Mateusz Piotrowski, Paul M. Riechers, Daniel Filan +1

What computational structures emerge in transformers trained on next-token prediction? In this work, we provide evidence that transformers implement constrained Bayesian belief upd…

cs.NE2022

Pruned Neural Networks are Surprisingly Modular

Daniel Filan, Shlomi Hod, Cody Wild +2

The learned weights of a neural network are often considered devoid of scrutable internal structure. To discern structure in these weights, we introduce a measurable notion of modu…

cs.LG2016

Loss Bounds and Time Complexity for Speed Priors

Daniel Filan, Marcus Hutter, Jan Leike

This paper establishes for the first time the predictive performance of speed priors and their computational complexity. A speed prior is essentially a probability distribution tha…

cs.CY2017

On the Impossibility of Supersized Machines

Ben Garfinkel, Miles Brundage, Daniel Filan +6

In recent years, a number of prominent computer scientists, along with academics in fields such as philosophy and physics, have lent credence to the notion that machines may one da…

cs.AI2018

Exploring Hierarchy-Aware Inverse Reinforcement Learning

Chris Cundy, Daniel Filan

We introduce a new generative model for human planning under the Bayesian Inverse Reinforcement Learning (BIRL) framework which takes into account the fact that humans often plan u…

quant-ph2015

What would it have looked like if it looked like I were in a superposition?

Daniel Filan, Joseph J. Hope

In this paper we address the question of whether it is possible to obtain evidence that we are in a superposition of different worlds, as suggested by the relative state interpreta…

cs.AI2016

Self-Modification of Policy and Utility Function in Rational Agents

Tom Everitt, Daniel Filan, Mayank Daswani +1

Any agent that is part of the environment it interacts with and has versatile actuators (such as arms and fingers), will in principle have the ability to self-modify -- for example…