Let F be a prime finite field. A code C⊂{Fn→F} is a subset of functions from Fn to F, where functions in the code are called codewords. The distance between two functions f,g:Fn→F is the fraction of coordinates where they disagree,

Let $f$ be a polynomial of degree $d$ in $n$ variables over a finite field $\mathbb{F}$. The polynomial is said to be unbiased if the distribution of…

We thank Matt Coudron and Matt Hastings for helpful discussions.

We ask, and answer, the question of what's computable by Turing machines equipped with time travel into the past: that is, closed timelike curves or …

Recent work has shown that deep neural networks are capable of approximating both value functions and policies in reinforcement learning domains feat…

Recent reinforcement learning (RL) approaches have shown strong performance in complex domains such as Atari games, but are often highly sample ineff…

It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good o…

In this paper, we consider regression problems with one-hidden-layer neural networks (1NNs). We distill some properties of activation functions that …

Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected …

Most publicly available image quality databases have been created under highly controlled conditions by introducing graded simulated distortions onto…

Solving the visual symbol grounding problem has long been a goal of artificial intelligence. The field appears to be advancing closer to this goal wi…

Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel ap…

The Neural GPU is a recent model that can learn algorithms such as multi-digit binary addition and binary multiplication in a way that generalizes to…

In this paper we consider the collaborative ranking setting: a pool of users each provides a small number of pairwise preferences between $d$ possibl…

We introduce a novel, simple convolution neural network (CNN) architecture - multi-group norm constraint CNN (MGNC-CNN) that capitalizes on multiple …

A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is bec…

We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sente…

We consider the problem of next frame prediction from video input. A recurrent convolutional neural network is trained to predict depth from monocula…

We present a video summarization approach for egocentric or "wearable" camera data. Given hours of video, the proposed method produces a compact stor…

We consider the problem of estimating a regression function in the common situation where the number of features is small, where interpretability of …

High-dimensional statistical inference deals with models in which the the number of parameters p is comparable to or larger than the sample size n. S…

One weakness of machine-learned NLP models is that they typically perform poorly on out-of-domain data. In this work, we study the task of identifyin…

By signing up you accept our content policy

Already have an account? Sign in

No a member yet? Create an account