Follow the ideas that keep turning up in Hacker News discussions.
Anders Sandberg, Eric Drexler, Toby Ord
The Fermi paradox is the conflict between an expectation of a high {\em ex ante} probability of intelligent life elsewhere in the universe and the apparently lifeless universe we in fact observe.
Chiyuan Zhang, Samy Bengio, Moritz Hardt +2
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.
Scott Aaronson
In honor of Alan Turing's hundredth birthday, I unwisely set out some thoughts about one of Turing's obsessions throughout his life, the question of physics and free will.
Art Hobson
Quantum foundations are still unsettled, with mixed effects on science and society.
Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio
Neural machine translation is a recently proposed approach to machine translation.
Nassim Nicholas Taleb
(The third edition corrects minor typos and adds 3 chapters synthesized from published papers plus an appendix on maximum entropy distributions.) The monograph investigates the misapplication of conventional statistical techniques to fat tailed distributions and looks for remedies, when possible.
Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan +1
Training of large-scale deep neural networks is often constrained by the available computational resources.
Kevin Meng, David Bau, Alex Andonian +1
We analyze the storage and recall of factual associations in autoregressive transformer language models, finding evidence that these associations correspond to localized, directly-editable computations.
Moritz Hardt, Eric Price, Nathan Srebro
We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features.
Andrew Gordon Wilson
Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization.
N. David Mermin
A strategy is suggested for teaching mathematically literate students, with no background in physics, just enough quantum mechanics for them to understand and develop algorithms in quantum computation and quantum information theory.
François Chollet
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.
Jonathan Frankle, Michael Carbin
Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy.
Emily M. Bender, Timnit Gebru, Angelina McMillan-Major +1
John Kirchenbauer, Jonas Geiping, Yuxin Wen +3
Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens.
Sara Sabour, Nicholas Frosst, Geoffrey E Hinton
A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part.
Henry W. Lin, Max Tegmark, David Rolnick
We show how the success of deep learning could depend not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can approximate arbitrary functions well, the class of functions of practical interest can frequently be approximated through "cheap learning" with exponentially fewer
Gavin A. Schmidt, Adam Frank
If an industrial civilization had existed on Earth many millions of years prior to our own era, what traces would it have left and would they be detectable today?
Max Tegmark
I explore physics implications of the External Reality Hypothesis (ERH) that there exists an external physical reality completely independent of us humans.
Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan +1
A central problem in machine learning involves modeling complex data-sets using highly flexible families of probability distributions in which learning, sampling, inference, and evaluation are still analytically or computationally tractable.
Nassim Nicholas Taleb, Rupert Read, Raphael Douady +2
We present a non-naive version of the Precautionary (PP) that allows us to avoid paranoia and paralysis by confining precaution to specific domains and problems.
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi +1
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability.
Joseph Redmon, Santosh Divvala, Ross Girshick +1
We present YOLO, a new approach to object detection.
David M. Blei, Alp Kucukelbir, Jon D. McAuliffe
One of the core problems of modern statistics is to approximate difficult-to-compute probability densities.
Robert E. Tarjan, Caleb C. Levy, Stephen Timmel
We introduce the zip tree, a form of randomized binary search tree that integrates previous ideas into one practical, performant, and pleasant-to-implement package.
Bobby Powers, David Tench, Emery D. Berger +1
Programs written in C/C++ can suffer from serious memory fragmentation, leading to low utilization of memory, degraded performance, and application failure due to memory exhaustion.
Johan Bollen, Huina Mao, Xiao-Jun Zeng
Behavioral economics tells us that emotions can profoundly affect individual behavior and decision-making.
Alexei A. Sharov, Richard Gordon
An extrapolation of the genetic complexity of organisms to earlier times suggests that life began before the Earth was formed.
Thomas Miconi
Various measures can be used to estimate bias or unfairness in a predictor.
Timothy Niven, Hung-Yu Kao
We are surprised to find that BERT's peak performance of 77% on the Argument Reasoning Comprehension Task reaches just three points below the average untrained human baseline.