Search Results for author:
Found 25 papers, 9 papers with code
Language models of protein sequences at the scale of evolution enable accurate structure prediction
We find that as models are scaled they learn information enabling the prediction of the three-dimensional structure of a protein at the resolution of individual atoms.
Language models enable zero-shot prediction of the effects of mutations on protein function
Modeling the effect of sequence variation on function is a fundamental problem for understanding and designing proteins.
MSA Transformer
Unsupervised protein language models trained across millions of diverse sequences learn structure and function of proteins.
Transformer protein language models are unsupervised structure learners
Unsupervised contact prediction is central to uncovering physical, structural, and functional constraints for protein structure determination and design.
Neural Potts Model
We propose the Neural Potts Model objective as an amortized optimization problem.
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
In the field of artificial intelligence, a combination of scale in data and model capacity enabled by unsupervised learning has led to major advances in representation learning and statistical generation.
Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics
De novo therapeutic design is challenged by a vast chemical repertoire and multiple constraints, e. g., high broad-spectrum potency and low toxicity.
Sobolev Independence Criterion
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.
Multi-Frame Cross-Entropy Training for Convolutional Neural Networks in Speech Recognition
We introduce Multi-Frame Cross-Entropy training (MFCE) for convolutional neural network acoustic models.
Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection
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.
Improved Adversarial Image Captioning
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.
Wasserstein Barycenter Model Ensembling
In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters.
PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences
Our model learns a rich latent space of the biological peptide context by taking advantage of abundant, unlabeled peptide sequences.
Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
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.
Sobolev Descent
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
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.
Semi-Supervised Learning with IPM-based GANs: an Empirical Study
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.
Sobolev GAN
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.
Fisher GAN
In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs.
English Conversational Telephone Speech Recognition by Humans and Machines
This then raises two issues - what IS human performance, and how far down can we still drive speech recognition error rates?
Ranked #3 on
Speech Recognition
on Switchboard + Hub500
McGan: Mean and Covariance Feature Matching GAN
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
We show that dense prediction view of framewise classification offers several advantages and insights, including computational efficiency and the ability to apply batch normalization.
The IBM 2016 English Conversational Telephone Speech Recognition System
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.
Ranked #5 on
Speech Recognition
on swb_hub_500 WER fullSWBCH
Advances in Very Deep Convolutional Neural Networks for LVCSR
We demonstrate the performance of our models both on larger scale data than before, and after sequence training.
Very Deep Multilingual Convolutional Neural Networks for LVCSR
However, CNNs in LVCSR have not kept pace with recent advances in other domains where deeper neural networks provide superior performance.
Ranked #17 on
Speech Recognition
on Switchboard + Hub500
