Search Results for author: Tom Sercu

Found 25 papers, 9 papers with code

Language models enable zero-shot prediction of the effects of mutations on protein function

1 code implementation NeurIPS 2021 Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu, Alex Rives

Modeling the effect of sequence variation on function is a fundamental problem for understanding and designing proteins.

MSA Transformer

1 code implementation13 Feb 2021 Roshan Rao, Jason Liu, Robert Verkuil, Joshua Meier, John F. Canny, Pieter Abbeel, Tom Sercu, Alexander Rives

Unsupervised protein language models trained across millions of diverse sequences learn structure and function of proteins.

Masked Language Modeling Multiple Sequence Alignment +1

Transformer protein language models are unsupervised structure learners

no code implementations ICLR 2021 Roshan Rao, Joshua Meier, Tom Sercu, Sergey Ovchinnikov, Alexander Rives

Unsupervised contact prediction is central to uncovering physical, structural, and functional constraints for protein structure determination and design.

Language Modelling

Neural Potts Model

no code implementations1 Jan 2021 Tom Sercu, Robert Verkuil, Joshua Meier, Brandon Amos, Zeming Lin, Caroline Chen, Jason Liu, Yann Lecun, Alexander Rives

We propose the Neural Potts Model objective as an amortized optimization problem.

Sobolev Independence Criterion

1 code implementation NeurIPS 2019 Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero dos Santos

In the kernel version we show that SIC can be cast as a convex optimization problem by introducing auxiliary variables that play an important role in feature selection as they are normalized feature importance scores.

Feature Importance feature selection

Multi-Frame Cross-Entropy Training for Convolutional Neural Networks in Speech Recognition

no code implementations29 Jul 2019 Tom Sercu, Neil Mallinar

We introduce Multi-Frame Cross-Entropy training (MFCE) for convolutional neural network acoustic models.

speech-recognition Speech Recognition

Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection

no code implementations ICLR Workshop DeepGenStruct 2019 Tom Sercu, Sebastian Gehrmann, Hendrik Strobelt, Payel Das, Inkit Padhi, Cicero dos Santos, Kahini Wadhawan, Vijil Chenthamarakshan

We present the pipeline in an interactive visual tool to enable the exploration of the metrics, analysis of the learned latent space, and selection of the best model for a given task.

Model Selection

Improved Adversarial Image Captioning

no code implementations ICLR Workshop DeepGenStruct 2019 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Tom Sercu

In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions.

Image Captioning

Wasserstein Barycenter Model Ensembling

1 code implementation13 Feb 2019 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Cicero dos Santos, Tom Sercu

In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters.

Attribute General Classification +2

PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences

no code implementations17 Oct 2018 Payel Das, Kahini Wadhawan, Oscar Chang, Tom Sercu, Cicero dos Santos, Matthew Riemer, Vijil Chenthamarakshan, Inkit Padhi, Aleksandra Mojsilovic

Our model learns a rich latent space of the biological peptide context by taking advantage of abundant, unlabeled peptide sequences.

Attribute

Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition

3 code implementations ICLR 2019 Chun-Fu Chen, Quanfu Fan, Neil Mallinar, Tom Sercu, Rogerio Feris

The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks, using popular architectures including ResNet and ResNeXt.

Object Object Recognition +2

Sobolev Descent

no code implementations30 May 2018 Youssef Mroueh, Tom Sercu, Anant Raj

We study a simplification of GAN training: the problem of transporting particles from a source to a target distribution.

Adversarial Semantic Alignment for Improved Image Captions

no code implementations30 Apr 2018 Pierre L. Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Tom Sercu

When evaluated on OOC and MS-COCO benchmarks, we show that SCST-based training has a strong performance in both semantic score and human evaluation, promising to be a valuable new approach for efficient discrete GAN training.

Image Captioning

Semi-Supervised Learning with IPM-based GANs: an Empirical Study

no code implementations7 Dec 2017 Tom Sercu, Youssef Mroueh

We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning.

General Classification

Sobolev GAN

2 code implementations ICLR 2018 Youssef Mroueh, Chun-Liang Li, Tom Sercu, Anant Raj, Yu Cheng

We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis.

Text Generation

Fisher GAN

2 code implementations NeurIPS 2017 Youssef Mroueh, Tom Sercu

In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs.

General Classification

McGan: Mean and Covariance Feature Matching GAN

no code implementations ICML 2017 Youssef Mroueh, Tom Sercu, Vaibhava Goel

We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN).

Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition

no code implementations28 Nov 2016 Tom Sercu, Vaibhava Goel

We show that dense prediction view of framewise classification offers several advantages and insights, including computational efficiency and the ability to apply batch normalization.

Computational Efficiency General Classification +3

The IBM 2016 English Conversational Telephone Speech Recognition System

no code implementations27 Apr 2016 George Saon, Tom Sercu, Steven Rennie, Hong-Kwang J. Kuo

We describe a collection of acoustic and language modeling techniques that lowered the word error rate of our English conversational telephone LVCSR system to a record 6. 6% on the Switchboard subset of the Hub5 2000 evaluation testset.

Language Modelling speech-recognition +1

Advances in Very Deep Convolutional Neural Networks for LVCSR

no code implementations6 Apr 2016 Tom Sercu, Vaibhava Goel

We demonstrate the performance of our models both on larger scale data than before, and after sequence training.

set matching speech-recognition +1

Very Deep Multilingual Convolutional Neural Networks for LVCSR

no code implementations29 Sep 2015 Tom Sercu, Christian Puhrsch, Brian Kingsbury, Yann Lecun

However, CNNs in LVCSR have not kept pace with recent advances in other domains where deeper neural networks provide superior performance.

speech-recognition Speech Recognition

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