In our paper, we propose a new scheme for continual learning of object detection, namely Contrast R-CNN, an approach strikes a balance between retaining the old knowledge and learning the new knowledge.
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties.
Our method is more flexible as it can handle both span answers and freeform answers.
We use the proposed criteria to select samples for strong and weak labelers to produce oracle labels and pseudo labels simultaneously at each active learning iteration in an ensemble learning manner, which can be examined with IoMT Platform.
In this paper, we propose SPNN - a Scalable and Privacy-preserving deep Neural Network learning framework, from algorithmic-cryptographic co-perspective.
More specifically, we proposed a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT based response ranker to rank the PRF-enhanced responses.
The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose.
In the era of big data, the need to expand the amount of data through data sharing to improve model performance has become increasingly compelling.
The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models.
To the best of our knowledge, our study is the first to provide a thorough analysis of the information leakage issues in deep transfer learning methods and provide potential solutions to the issue.
Specifically, CNN is utilized to model the spatial relations and the short-term temporal dependencies among sensors, while the output features of CNN are fed into the GRU to learn the long-term temporal dependencies jointly.
We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
Canonical automatic summary evaluation metrics, such as ROUGE, suffer from two drawbacks.
The insurance industry has been creating innovative products around the emerging online shopping activities.
We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.
Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent.
First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way.
With the explosive growth of e-commerce and the booming of e-payment, detecting online transaction fraud in real time has become increasingly important to Fintech business.
In this study, we applied powerful deep neural network and explored a process in the forecast of skeletal bone age with the specifically combine joints images to increase the performance accuracy compared with the whole hand images.
Product reviews, in the form of texts dominantly, significantly help consumers finalize their purchasing decisions.
With the growing amount of reviews in e-commerce websites, it is critical to assess the helpfulness of reviews and recommend them accordingly to consumers.
We present a deep learning framework for computer-aided lung cancer diagnosis.
Recent work on aspect extraction is leveraging the hierarchical relationship between products and their categories.