We propose a novel “Semantic Deep Learning” method to analyze the electronic health records of real patients. Our previous work as successfully used a hypergraph- based approach in the clinical text notes from Stanford Hospital’s Clinical Data Warehouse (STRIDE).
The goal of this project is to evaluate contemporary techniques for deep learning model explanations and utilize DL Explanation approach for improving model interpretability.
In this project, we will investigate ontology-based explainable deep learning (OBDL) algorithms for textual data to identify key factors, concepts, and hypothesis that significantly contribute to the decision made by deep neural networks.
Short text Matching plays an important role in natural language processing tasks such as information retrieval (IR), question answering (QA), and dialogue system. Traditional text matching methods rely on human-crafted rules and template. Though they are effective to deal with specific situations, but lack in the ability to handle unobserved cases. In natural language, it’s infeasible to exhaust every possible expression that conveys the same ideas. Recently, neural network-based models have good generalizability to unobserved cases but provide less interpretability. In this project, we aim to balance the two sides by introducing the concept of entity to QA. We propose an interpretable, deep learning-based short text matching model for customer service domain question answering, which consists of two major components: Word segmentation enhanced Named Entity Recognition (NER), and text semantic matching. By doing so, the proposed method explicitly models entities and types of entity as building blocks of interpretable QA.
DeepSLAM project is designed to develop an end-to-end and all-in-one deep neural network capable of followings, simultaneously, with only road scene RGB images
(a) Object Detection using RGB images and videos;
(b) Object Re-identification over multiple frames, with occlusions;
(c) Predicting multiple object’s future trajectories.
This all-in-one solution provides a better level of information integrity and reuse. In doing so, a local belief of the surrounding area will be trained with grid cells, a navigation system in humans’ brain, to generate a local implicit map to capture dynamic road condition. Then local coarse implicit mapping is then combined with global accurate road information for above three goals.
The goal of this project is to design and develop an intelligent task management for online education and business purpose. The project includes OneTask online platform, self-adaptive neural question generation for study quality evaluation and companion, GCN-based DRL model for self-adaptive neural question generation and study content recommendation and entity-related open-domain question answering system.
The goal of this project is to develop a Deep Neural Network based risk management model that can help financial companies predict loan default likelihood with a higher accuracy when a customer applies for a loan.
The goal of this project is to explore potential vulnerabilities in federated learning applications. Federated learning is a new kind of distributed machine learning with decentralized data. There is no need for data sharing for federated learning.
The goal of this work is to translate streams of data from individual sensors into a shared manifold-space for joint understanding and processing. This work includes investigation of computational topology for manifold learning, data summarization, and intrinsic dimensionality estimation. In practice, for a given application, processing chains are generally developed for a particular sensor or set of sensors.
Deep learning (DL) has in recent years been widely used in computer vision and natural language processing (NLP) applications due to its superior performance. However, while images and natural languages are known to be rich in structures expressed, for example, by grammar rules, DL has so far not been capable of explicitly representing and enforcing such structures. In this project, we propose an approach to bridging this gap by exploiting tensor product representations (TPR), a structured neural-symbolic model developed in cognitive science, aiming to integrate DL with explicit language rules, logical rules, or rules that summarize the human knowledge about the subject.