Search Results for author: W. Ronny Huang

Found 19 papers, 8 papers with code

Analyzing the effect of neural network architecture on training performance

no code implementations ICML 2020 Karthik Abinav Sankararaman, Soham De, Zheng Xu, W. Ronny Huang, Tom Goldstein

Through novel theoretical and experimental results, we show how the neural net architecture affects gradient confusion, and thus the efficiency of training.

E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR

no code implementations22 Apr 2022 W. Ronny Huang, Shuo-Yiin Chang, David Rybach, Rohit Prabhavalkar, Tara N. Sainath, Cyril Allauzen, Cal Peyser, Zhiyun Lu

Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition.

Speech Recognition

Detecting Unintended Memorization in Language-Model-Fused ASR

no code implementations20 Apr 2022 W. Ronny Huang, Steve Chien, Om Thakkar, Rajiv Mathews

End-to-end (E2E) models are often being accompanied by language models (LMs) via shallow fusion for boosting their overall quality as well as recognition of rare words.

Language Modelling

Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition

no code implementations9 Mar 2022 W. Ronny Huang, Cal Peyser, Tara N. Sainath, Ruoming Pang, Trevor Strohman, Shankar Kumar

We down-select a large corpus of web search queries by a factor of 53x and achieve better LM perplexities than without down-selection.

Speech Recognition

Scaling End-to-End Models for Large-Scale Multilingual ASR

no code implementations30 Apr 2021 Bo Li, Ruoming Pang, Tara N. Sainath, Anmol Gulati, Yu Zhang, James Qin, Parisa Haghani, W. Ronny Huang, Min Ma, Junwen Bai

Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data.

Multi-Task Learning

Lookup-Table Recurrent Language Models for Long Tail Speech Recognition

no code implementations9 Apr 2021 W. Ronny Huang, Tara N. Sainath, Cal Peyser, Shankar Kumar, David Rybach, Trevor Strohman

We introduce Lookup-Table Language Models (LookupLM), a method for scaling up the size of RNN language models with only a constant increase in the floating point operations, by increasing the expressivity of the embedding table.

Speech Recognition

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching

1 code implementation ICLR 2021 Jonas Geiping, Liam Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, Tom Goldstein

We consider a particularly malicious poisoning attack that is both "from scratch" and "clean label", meaning we analyze an attack that successfully works against new, randomly initialized models, and is nearly imperceptible to humans, all while perturbing only a small fraction of the training data.

Data Poisoning

MetaPoison: Practical General-purpose Clean-label Data Poisoning

2 code implementations NeurIPS 2020 W. Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, Tom Goldstein

Existing attacks for data poisoning neural networks have relied on hand-crafted heuristics, because solving the poisoning problem directly via bilevel optimization is generally thought of as intractable for deep models.

AutoML Bilevel Optimization +2

DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images

2 code implementations NeurIPS Workshop Document_Intelligen 2019 W. Ronny Huang, Yike Qi, Qianqian Li, Jonathan Degange

In addition to high segmentation accuracy, we show that our cleansed images achieve a significant boost in recognition accuracy by popular OCR software such as Tesseract 4. 0.

Optical Character Recognition

Deep k-NN Defense against Clean-label Data Poisoning Attacks

1 code implementation29 Sep 2019 Neehar Peri, Neal Gupta, W. Ronny Huang, Liam Fowl, Chen Zhu, Soheil Feizi, Tom Goldstein, John P. Dickerson

Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a particular test sample during inference.

Adversarial Attack Data Poisoning

The Effect of Neural Net Architecture on Gradient Confusion & Training Performance

no code implementations25 Sep 2019 Karthik A. Sankararaman, Soham De, Zheng Xu, W. Ronny Huang, Tom Goldstein

Through novel theoretical and experimental results, we show how the neural net architecture affects gradient confusion, and thus the efficiency of training.

Understanding Generalization through Visualizations

2 code implementations NeurIPS Workshop ICBINB 2020 W. Ronny Huang, Zeyad Emam, Micah Goldblum, Liam Fowl, Justin K. Terry, Furong Huang, Tom Goldstein

The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive.

Transferable Clean-Label Poisoning Attacks on Deep Neural Nets

1 code implementation15 May 2019 Chen Zhu, W. Ronny Huang, Ali Shafahi, Hengduo Li, Gavin Taylor, Christoph Studer, Tom Goldstein

Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data.

Transfer Learning

The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent

no code implementations15 Apr 2019 Karthik A. Sankararaman, Soham De, Zheng Xu, W. Ronny Huang, Tom Goldstein

Our results show that, for popular initialization techniques, increasing the width of neural networks leads to lower gradient confusion, and thus faster model training.

Accurate, Data-Efficient Learning from Noisy, Choice-Based Labels for Inherent Risk Scoring

no code implementations27 Nov 2018 W. Ronny Huang, Miguel A. Perez

The data collection is synthetic; examples are crafted using optimal experimental design methods, obviating the need for real data which is often difficult to obtain due to regulatory concerns.

Experimental Design

Are adversarial examples inevitable?

no code implementations ICLR 2019 Ali Shafahi, W. Ronny Huang, Christoph Studer, Soheil Feizi, Tom Goldstein

Using experiments, we explore the implications of theoretical guarantees for real-world problems and discuss how factors such as dimensionality and image complexity limit a classifier's robustness against adversarial examples.

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