Toyota Technological Institute at Chicago

∙ Chicago , United States ∙ 0 followers

Toyota Technological Institute at Chicago is a philanthropically endowed academic computer science institute, dedicated to basic research and graduate education in computer science.

Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?

Multiple fairness constraints have been proposed in the literature, moti...
12/02/2019 ∙ by Avrim Blum, et al. ∙ 35 ∙ share

read it
Deformable Style Transfer

Both geometry and texture are fundamental aspects of visual style. Exist...
03/24/2020 ∙ by Sunnie S. Y. Kim, et al. ∙ 26 ∙ share

read it
Style Transfer by Relaxed Optimal Transport and Self-Similarity

Style transfer algorithms strive to render the content of one image usin...
04/29/2019 ∙ by Nicholas Kolkin, et al. ∙ 16 ∙ share

read it
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Increasing model size when pretraining natural language representations ...
09/26/2019 ∙ by Zhenzhong Lan, et al. ∙ 11 ∙ share

read it
Fingerspelling recognition in the wild with iterative visual attention

Sign language recognition is a challenging gesture sequence recognition ...
08/28/2019 ∙ by Bowen Shi, et al. ∙ 10 ∙ share

read it
Pixel Consensus Voting for Panoptic Segmentation

The core of our approach, Pixel Consensus Voting, is a framework for ins...
04/04/2020 ∙ by Haochen Wang, et al. ∙ 9 ∙ share

read it
Growing Efficient Deep Networks by Structured Continuous Sparsification

We develop an approach to training deep networks while dynamically adjus...
07/30/2020 ∙ by Xin Yuan, et al. ∙ 9 ∙ share

read it
Deep Anomaly Detection with Outlier Exposure

It is important to detect and handle anomalous inputs when deploying mac...
12/11/2018 ∙ by Dan Hendrycks, et al. ∙ 8 ∙ share

read it
Benchmarking Approximate Inference Methods for Neural Structured Prediction

Exact structured inference with neural network scoring functions is comp...
04/01/2019 ∙ by Lifu Tu, et al. ∙ 6 ∙ share

read it
Natural Adversarial Examples

We introduce natural adversarial examples -- real-world, unmodified, and...
07/16/2019 ∙ by Dan Hendrycks, et al. ∙ 6 ∙ share

read it
Domain-independent Dominance of Adaptive Methods

From a simplified analysis of adaptive methods, we derive AvaGrad, a new...
12/04/2019 ∙ by Pedro Savarese, et al. ∙ 6 ∙ share

read it
Is Local SGD Better than Minibatch SGD?

We study local SGD (also known as parallel SGD and federated averaging),...
02/18/2020 ∙ by Blake Woodworth, et al. ∙ 5 ∙ share

read it
Recurrent Back-Projection Network for Video Super-Resolution

We proposed a novel architecture for the problem of video super-resoluti...
03/25/2019 ∙ by Muhammad Haris, et al. ∙ 4 ∙ share

read it
Generating Diverse Story Continuations with Controllable Semantics

We propose a simple and effective modeling framework for controlled gene...
09/30/2019 ∙ by Lifu Tu, et al. ∙ 4 ∙ share

read it
Task-Driven Super Resolution: Object Detection in Low-resolution Images

We consider how image super resolution (SR) can contribute to an object ...
03/30/2018 ∙ by Muhammad Haris, et al. ∙ 2 ∙ share

read it
Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks

Despite existing work on ensuring generalization of neural networks in t...
05/30/2018 ∙ by Behnam Neyshabur, et al. ∙ 2 ∙ share

read it
End-to-End Content and Plan Selection for Data-to-Text Generation

Learning to generate fluent natural language from structured data with n...
10/10/2018 ∙ by Sebastian Gehrmann, et al. ∙ 2 ∙ share

read it
Visually Grounded Neural Syntax Acquisition

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an appr...
06/07/2019 ∙ by Haoyue Shi, et al. ∙ 2 ∙ share

read it
Advancing subgroup fairness via sleeping experts

We study methods for improving fairness to subgroups in settings with ov...
09/18/2019 ∙ by Avrim Blum, et al. ∙ 1 ∙ share

read it
The Strategic Perceptron

The classical Perceptron algorithm provides a simple and elegant procedu...
08/04/2020 ∙ by Saba Ahmadi, et al. ∙ 1 ∙ share

read it
Multilingual Speech Recognition With A Single End-To-End Model

Training a conventional automatic speech recognition (ASR) system to sup...
11/06/2017 ∙ by Shubham Toshniwal, et al. ∙ 0 ∙ share

read it
From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets

We propose a Las Vegas transformation of Markov Chain Monte Carlo (MCMC)...
11/22/2017 ∙ by Pedro H. P. Savarese, et al. ∙ 0 ∙ share

read it
Active Tolerant Testing

In this work, we give the first algorithms for tolerant testing of nontr...
11/01/2017 ∙ by Avrim Blum, et al. ∙ 0 ∙ share

read it
Multigrid Neural Architectures

We propose a multigrid extension of convolutional neural networks (CNNs)...
11/23/2016 ∙ by Tsung-Wei Ke, et al. ∙ 0 ∙ share

read it
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

We consider the two related problems of detecting if an example is miscl...
10/07/2016 ∙ by Dan Hendrycks, et al. ∙ 0 ∙ share

read it
Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition

We address the problem of automatic American Sign Language fingerspellin...
10/09/2017 ∙ by Bowen Shi, et al. ∙ 0 ∙ share

read it
Multiplicative LSTM for sequence modelling

We introduce multiplicative LSTM (mLSTM), a recurrent neural network arc...
09/26/2016 ∙ by Ben Krause, et al. ∙ 0 ∙ share

read it
Semantic keyword spotting by learning from images and speech

We consider the problem of representing semantic concepts in speech by l...
10/05/2017 ∙ by Herman Kamper, et al. ∙ 0 ∙ share

read it
Early Methods for Detecting Adversarial Images

Many machine learning classifiers are vulnerable to adversarial perturba...
08/01/2016 ∙ by Dan Hendrycks, et al. ∙ 0 ∙ share

read it
Adjusting for Dropout Variance in Batch Normalization and Weight Initialization

We show how to adjust for the variance introduced by dropout with correc...
07/08/2016 ∙ by Dan Hendrycks, et al. ∙ 0 ∙ share

read it
Sequence Training and Adaptation of Highway Deep Neural Networks

Highway deep neural network (HDNN) is a type of depth-gated feedforward ...
07/07/2016 ∙ by Liang Lu, et al. ∙ 0 ∙ share

read it
Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation

We study the problem of recognition of fingerspelled letter sequences in...
02/13/2016 ∙ by Taehwan Kim, et al. ∙ 0 ∙ share

read it
Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding

Spectral embedding provides a framework for solving perceptual organizat...
12/09/2015 ∙ by Michael Maire, et al. ∙ 0 ∙ share

read it
Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition

End-to-end training of deep learning-based models allows for implicit le...
04/05/2017 ∙ by Shubham Toshniwal, et al. ∙ 0 ∙ share

read it
Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis

We study the problem of acoustic feature learning in the setting where w...
08/11/2017 ∙ by Qingming Tang, et al. ∙ 0 ∙ share

read it
Training Deep Networks to be Spatially Sensitive

In many computer vision tasks, for example saliency prediction or semant...
08/07/2017 ∙ by Nicholas Kolkin, et al. ∙ 0 ∙ share

read it
Implicit Regularization in Matrix Factorization

We study implicit regularization when optimizing an underdetermined quad...
05/25/2017 ∙ by Suriya Gunasekar, et al. ∙ 0 ∙ share

read it
Norm-Based Capacity Control in Neural Networks

We investigate the capacity, convexity and characterization of a general...
02/27/2015 ∙ by Behnam Neyshabur, et al. ∙ 0 ∙ share

read it
Coherent Dialogue with Attention-based Language Models

We model coherent conversation continuation via RNN-based dialogue model...
11/21/2016 ∙ by Hongyuan Mei, et al. ∙ 0 ∙ share

read it
Jointly Learning to Align and Convert Graphemes to Phonemes with Neural Attention Models

We propose an attention-enabled encoder-decoder model for the problem of...
10/20/2016 ∙ by Shubham Toshniwal, et al. ∙ 0 ∙ share

read it
Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation

Modern robotics applications that involve human-robot interaction requir...
10/11/2016 ∙ by Andrea F. Daniele, et al. ∙ 0 ∙ share

read it
Stochastic Canonical Correlation Analysis

We tightly analyze the sample complexity of CCA, provide a learning algo...
02/21/2017 ∙ by Chao Gao, et al. ∙ 0 ∙ share

read it
Stabilizing GAN Training with Multiple Random Projections

Training generative adversarial networks is unstable in high-dimensions ...
05/22/2017 ∙ by Behnam Neyshabur, et al. ∙ 0 ∙ share

read it
Corralling a Band of Bandit Algorithms

We study the problem of combining multiple bandit algorithms (that is, o...
12/19/2016 ∙ by Alekh Agarwal, et al. ∙ 0 ∙ share

read it
Satellite Image-based Localization via Learned Embeddings

We propose a vision-based method that localizes a ground vehicle using p...
04/04/2017 ∙ by Dong-Ki Kim, et al. ∙ 0 ∙ share

read it
Visually grounded learning of keyword prediction from untranscribed speech

During language acquisition, infants have the benefit of visual cues to ...
03/23/2017 ∙ by Herman Kamper, et al. ∙ 0 ∙ share

read it
End-to-End Training Approaches for Discriminative Segmental Models

Recent work on discriminative segmental models has shown that they can a...
10/21/2016 ∙ by Hao Tang, et al. ∙ 0 ∙ share

read it
Single Pass PCA of Matrix Products

In this paper we present a new algorithm for computing a low rank approx...
10/21/2016 ∙ by Shanshan Wu, et al. ∙ 0 ∙ share

read it
Colorization as a Proxy Task for Visual Understanding

We investigate and improve self-supervision as a drop-in replacement for...
03/11/2017 ∙ by Gustav Larsson, et al. ∙ 0 ∙ share

read it
Comprehension-guided referring expressions

We consider generation and comprehension of natural language referring e...
01/12/2017 ∙ by Ruotian Luo, et al. ∙ 0 ∙ share

read it

Toyota Technological Institute at Chicago

Featured Researchers