Search Results for author: Ian J. Goodfellow

Found 13 papers, 10 papers with code

Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

6 code implementations NeurIPS 2018 Avital Oliver, Augustus Odena, Colin Raffel, Ekin D. Cubuk, Ian J. Goodfellow

However, we argue that these benchmarks fail to address many issues that these algorithms would face in real-world applications.

Explaining and Harnessing Adversarial Examples

49 code implementations20 Dec 2014 Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy

Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence.

Image Classification

On distinguishability criteria for estimating generative models

1 code implementation19 Dec 2014 Ian J. Goodfellow

However, we show that recovering MLE for a learned generator requires departing from the distinguishability game.

Qualitatively characterizing neural network optimization problems

1 code implementation19 Dec 2014 Ian J. Goodfellow, Oriol Vinyals, Andrew M. Saxe

Training neural networks involves solving large-scale non-convex optimization problems.

Generative Adversarial Networks

168 code implementations Proceedings of the 27th International Conference on Neural Information Processing Systems 2014 Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.

An empirical analysis of dropout in piecewise linear networks

no code implementations21 Dec 2013 David Warde-Farley, Ian J. Goodfellow, Aaron Courville, Yoshua Bengio

The recently introduced dropout training criterion for neural networks has been the subject of much attention due to its simplicity and remarkable effectiveness as a regularizer, as well as its interpretation as a training procedure for an exponentially large ensemble of networks that share parameters.

Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

16 code implementations20 Dec 2013 Ian J. Goodfellow, Yaroslav Bulatov, Julian Ibarz, Sacha Arnoud, Vinay Shet

In this paper we propose a unified approach that integrates these three steps via the use of a deep convolutional neural network that operates directly on the image pixels.

Image Classification

On the Challenges of Physical Implementations of RBMs

no code implementations18 Dec 2013 Vincent Dumoulin, Ian J. Goodfellow, Aaron Courville, Yoshua Bengio

Restricted Boltzmann machines (RBMs) are powerful machine learning models, but learning and some kinds of inference in the model require sampling-based approximations, which, in classical digital computers, are implemented using expensive MCMC.

Maxout Networks

6 code implementations18 Feb 2013 Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, Yoshua Bengio

We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout.

General Classification Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.