Title: General Multi-label Image Classification with Transformers
Deep Learning's Generalization, Especially on structured discrete data
Background on why Generalization topics of Deep Learning are interesting?
Generalization refers to how a machine model adapts properly to new, previously unseen data.
Background on Representation Learning and Deep Learning
The performance of machine learning algorithms is largely dependent on the data representation (or features) on which they are applied. Deep learning aims at discovering learning algorithms that can find multiple levels of representations directly from data, with higher levels representing more abstract concepts. In recent years, the field of deep learning has lead to groundbreaking performance in many applications such as computer vision, speech understanding, natural language processing, and computational biology.
Why structured discrete Data is Interesting?
Deep learning constructs networks of parameterized functional modules and is trained from reference examples using gradient-based optimization [Lecun19].
Since it is hard to estimate gradients through functions of discrete random variables, researching on how to make deep learning behave well on discrete structured data and structured representation interests us. Developing such techniques are an active research area. We focus on investigating interpretable and scalable techniques for doing so.
Relevant Papers we published
- Please check out each item in our side-bar
We have focused on weak supervision in multiple of our papers along this line of research.
Thanks for reading!
Title: Curriculum Labeling- Self-paced Pseudo-Labeling for Semi-Supervised Learning”
Transfer Learning with Motif Transformers for Predicting Protein-Protein Interactions Between a Novel Virus and Humans
Title: Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples
Title: Reevaluating Adversarial Examples in Natural Language
MUST-CNN- A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
Tool MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
Title: Deep Learning for Character-based Information Extraction on Chinese and Protein Sequence
Tool Multitask-ProteinTagging: A unified multitask architecture for predicting local protein properties
Paper0: Learning to rank with (a lot of) word features