Search Results for author:
Found 15 papers, 7 papers with code
Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency.
Xtal2DoS: Attention-based Crystal to Sequence Learning for Density of States Prediction
Modern machine learning techniques have been extensively applied to materials science, especially for property prediction tasks.
Efficient Domain Adaptation for Speech Foundation Models
The FM encoder adapter and decoder are then finetuned to the target domain with a small amount of supervised in-domain data.
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
We find that by using contrastive learning in the supervised setting, we can exploit label information effectively in a data-driven manner, and learn meaningful feature and label embeddings which capture the label correlations and enhance the predictive power.
A GNN-RNN Approach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction
As far as we know, this is the first machine learning method that embeds geographical knowledge in crop yield prediction and predicts the crop yields at county level nationwide.
Joint Unsupervised and Supervised Training for Multilingual ASR
Our average WER of all languages outperforms average monolingual baseline by 33. 3%, and the state-of-the-art 2-stage XLSR by 32%.
Contrastively Disentangled Sequential Variational Autoencoder
We propose a novel sequence representation learning method, named Contrastively Disentangled Sequential Variational Autoencoder (C-DSVAE), to extract and separate the static (time-invariant) and dynamic (time-variant) factors in the latent space.
Scaling End-to-End Models for Large-Scale Multilingual ASR
Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data.
HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders
This in turn leads to a challenging and long-standing problem in the field of computer science - how to perform ac-curate multi-label classification with hundreds of labels?
Deep Hurdle Networks for Zero-Inflated Multi-Target Regression: Application to Multiple Species Abundance Estimation
A key problem in computational sustainability is to understand the distribution of species across landscapes over time.
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations of sequence data should exhibit a simple structure in the latent space.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model
The decoder of MPVAE takes in the samples from the embedding spaces and models the joint distribution of output targets under a Multivariate Probit model by learning a shared covariance matrix.
SWALP : Stochastic Weight Averaging in Low-Precision Training
Low precision operations can provide scalability, memory savings, portability, and energy efficiency.
End-to-End Refinement Guided by Pre-trained Prototypical Classifier
We propose imitation refinement, a novel approach to refine imperfect input patterns, guided by a pre-trained classifier incorporating prior knowledge from simulated theoretical data, such that the refined patterns imitate the ideal data.
Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery
A key problem in materials discovery, the phase map identification problem, involves the determination of the crystal phase diagram from the materials' composition and structural characterization data.
