We also trained state-of-the-art ML models on this dataset to approximate calculations at the DFT level.
We propose the Spherical Channel Network (SCN) to model atomic energies and forces.
Self-supervised learning (SSL) of speech representations has received much attention over the last few years but most work has focused on languages and domains with an abundance of unlabeled data.
2 code implementations • 17 Jun 2022 • Richard Tran, Janice Lan, Muhammed Shuaibi, Brandon M. Wood, Siddharth Goyal, Abhishek Das, Javier Heras-Domingo, Adeesh Kolluru, Ammar Rizvi, Nima Shoghi, Anuroop Sriram, Felix Therrien, Jehad Abed, Oleksandr Voznyy, Edward H. Sargent, Zachary Ulissi, C. Lawrence Zitnick
The development of machine learning models for electrocatalysts requires a broad set of training data to enable their use across a wide variety of materials.
This work investigates this question by first developing the GemNet-OC model based on the large Open Catalyst 2020 (OC20) dataset.
Ranked #1 on Initial Structure to Relaxed Energy (IS2RE) on OC20
Recent progress in Graph Neural Networks (GNNs) for modeling atomic simulations has the potential to revolutionize catalyst discovery, which is a key step in making progress towards the energy breakthroughs needed to combat climate change.
Ranked #2 on Initial Structure to Relaxed Energy (IS2RE) on OC20
We introduce a novel approach to modeling angular information between sets of neighboring atoms in a graph neural network.
Ranked #3 on Initial Structure to Relaxed Energy (IS2RE) on OC20
2 code implementations • 2 Apr 2021 • Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli
On a large-scale competitive setup, we show that pre-training on unlabeled in-domain data reduces the gap between models trained on in-domain and out-of-domain labeled data by 66%-73%.
By not imposing explicit physical constraints, we can flexibly design expressive models while maintaining their computational efficiency.
1 code implementation • 13 Jan 2021 • Anuroop Sriram, Matthew Muckley, Koustuv Sinha, Farah Shamout, Joelle Pineau, Krzysztof J. Geras, Lea Azour, Yindalon Aphinyanaphongs, Nafissa Yakubova, William Moore
The first is deterioration prediction from a single image, where our model achieves an area under receiver operating characteristic curve (AUC) of 0. 742 for predicting an adverse event within 96 hours (compared to 0. 703 with supervised pretraining) and an AUC of 0. 765 for predicting oxygen requirements greater than 6 L a day at 24 hours (compared to 0. 749 with supervised pretraining).
We use ForceNet to perform quantum chemistry simulations, where ForceNet is able to achieve 4x higher success rate than existing ML models.
3 code implementations • 9 Dec 2020 • Matthew J. Muckley, Bruno Riemenschneider, Alireza Radmanesh, Sunwoo Kim, Geunu Jeong, Jingyu Ko, Yohan Jun, Hyungseob Shin, Dosik Hwang, Mahmoud Mostapha, Simon Arberet, Dominik Nickel, Zaccharie Ramzi, Philippe Ciuciu, Jean-Luc Starck, Jonas Teuwen, Dimitrios Karkalousos, Chaoping Zhang, Anuroop Sriram, Zhengnan Huang, Nafissa Yakubova, Yvonne Lui, Florian Knoll
Accelerating MRI scans is one of the principal outstanding problems in the MRI research community.
This paper introduces Multilingual LibriSpeech (MLS) dataset, a large multilingual corpus suitable for speech research.
5 code implementations • 20 Oct 2020 • Lowik Chanussot, Abhishek Das, Siddharth Goyal, Thibaut Lavril, Muhammed Shuaibi, Morgane Riviere, Kevin Tran, Javier Heras-Domingo, Caleb Ho, Weihua Hu, Aini Palizhati, Anuroop Sriram, Brandon Wood, Junwoong Yoon, Devi Parikh, C. Lawrence Zitnick, Zachary Ulissi
Catalyst discovery and optimization is key to solving many societal and energy challenges including solar fuels synthesis, long-term energy storage, and renewable fertilizer production.
no code implementations • 14 Oct 2020 • C. Lawrence Zitnick, Lowik Chanussot, Abhishek Das, Siddharth Goyal, Javier Heras-Domingo, Caleb Ho, Weihua Hu, Thibaut Lavril, Aini Palizhati, Morgane Riviere, Muhammed Shuaibi, Anuroop Sriram, Kevin Tran, Brandon Wood, Junwoong Yoon, Devi Parikh, Zachary Ulissi
As we increase our reliance on renewable energy sources such as wind and solar, which produce intermittent power, storage is needed to transfer power from times of peak generation to peak demand.
We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse languages.
The slow acquisition speed of magnetic resonance imaging (MRI) has led to the development of two complementary methods: acquiring multiple views of the anatomy simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing methods (compressed sensing).
Ranked #1 on MRI Reconstruction on fastMRI Knee 4x
1 code implementation • 6 Jan 2020 • Florian Knoll, Tullie Murrell, Anuroop Sriram, Nafissa Yakubova, Jure Zbontar, Michael Rabbat, Aaron Defazio, Matthew J. Muckley, Daniel K. Sodickson, C. Lawrence Zitnick, Michael P. Recht
Conclusion: The challenge led to new developments in machine learning for image reconstruction, provided insight into the current state of the art in the field, and highlighted remaining hurdles for clinical adoption.
We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions.
Ranked #15 on Speech Recognition on LibriSpeech test-other (using extra training data)
Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic model, language model, punctuation model, inverse text normalization) into one single model.
In this paper, we present a novel method to integrate traditional parallel imaging methods into deep neural networks that is able to generate high quality reconstructions even for high acceleration factors.
11 code implementations • 21 Nov 2018 • Jure Zbontar, Florian Knoll, Anuroop Sriram, Tullie Murrell, Zhengnan Huang, Matthew J. Muckley, Aaron Defazio, Ruben Stern, Patricia Johnson, Mary Bruno, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzal, Adriana Romero, Michael Rabbat, Pascal Vincent, Nafissa Yakubova, James Pinkerton, Duo Wang, Erich Owens, C. Lawrence Zitnick, Michael P. Recht, Daniel K. Sodickson, Yvonne W. Lui
Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applications where it is currently prohibitively slow or expensive.
This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition.
Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition.
In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition.
no code implementations • 11 May 2017 • Eric Battenberg, Rewon Child, Adam Coates, Christopher Fougner, Yashesh Gaur, Jiaji Huang, Heewoo Jun, Ajay Kannan, Markus Kliegl, Atul Kumar, Hairong Liu, Vinay Rao, Sanjeev Satheesh, David Seetapun, Anuroop Sriram, Zhenyao Zhu
Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition.