User profiles for I. Goodfellow

Ian Goodfellow

DeepMind
Verified email at deepmind.com
Cited by 284180

Goodfellow I

PA Goodfellow, X Mirza… - Pouget-Abadie J …, 2014 - springfieldsfirstschool.org.uk
E Goodfellow Page 1 SPRINGFIELDS FIRST SCHOOL Yarnfield, Stone, Staffordshire, ST15
0NJ ‘ACHIEVING EXCELLENCE TOGETHER’ Headteacher Telephone: 01785 337310 Alison …

Generative adversarial networks

I Goodfellow, J Pouget-Abadie, M Mirza, B Xu… - Communications of the …, 2020 - dl.acm.org
Generative adversarial networks are a kind of artificial intelligence algorithm designed to
solve the generative modeling problem. The goal of a generative model is to study a collection …

[BOOK][B] Deep learning

I Goodfellow, Y Bengio, A Courville - 2016 - books.google.com
An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research perspectives.“…

Generative adversarial nets

I Goodfellow, J Pouget-Abadie… - Advances in neural …, 2014 - proceedings.neurips.cc
We propose a new framework for estimating generative models via adversarial nets, in
which we simultaneously train two models: a generative model G that captures the data …

[BOOK][B] Deep learning

Y Bengio, I Goodfellow, A Courville - 2017 - academia.edu
Inventors have long dreamed of creating machines that think. Ancient Greek myths tell of
intelligent objects, such as animated statues of human beings and tables that arrive full of food …

Explaining and harnessing adversarial examples

IJ Goodfellow, J Shlens, C Szegedy - arXiv preprint arXiv:1412.6572, 2014 - arxiv.org
Several machine learning models, including neural networks, consistently misclassify adversarial
examples---inputs formed by applying small but intentionally worst-case perturbations …

Maxout networks

I Goodfellow, D Warde-Farley, M Mirza… - International …, 2013 - proceedings.mlr.press
We consider the problem of designing models to leverage a recently introduced approximate
model averaging technique called dropout. We define a simple new model called maxout (…

Improved techniques for training gans

T Salimans, I Goodfellow, W Zaremba… - Advances in neural …, 2016 - proceedings.neurips.cc
We present a variety of new architectural features and training procedures that we apply to
the generative adversarial networks (GANs) framework. Using our new techniques, we …

Theano: A Python framework for fast computation of mathematical expressions

…, O Firat, M Germain, X Glorot, I Goodfellow… - arXiv e …, 2016 - ui.adsabs.harvard.edu
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions
involving multi-dimensional arrays efficiently. Since its introduction, it has been one of …

Adversarial machine learning at scale

A Kurakin, I Goodfellow, S Bengio - arXiv preprint arXiv:1611.01236, 2016 - arxiv.org
Adversarial examples are malicious inputs designed to fool machine learning models. They
often transfer from one model to another, allowing attackers to mount black box attacks …