Chao Zhang

Qian Feng, Hanbin Zhao, Chao Zhang et al.

Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID information at the inference time. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples (rehearsal-free) and with a memory constraint (memory-constrained): Prompt-extending and Prompt-fixed methods. However, prompt-extending methods need a large memory buffer to maintain an ever-expanding prompt pool and meet an extra challenging prompt selection problem. Prompt-fixed methods only learn a single set of prompts on one of the incremental tasks and can not handle all the incremental tasks effectively. To achieve a good balance between the memory cost and the performance on all the tasks, we propose a Parameter-Efficient Cross-Task Prompt (PECTP) framework with Prompt Retention Module (PRM) and classifier Head Retention Module (HRM). To make the final learned prompts effective on all incremental tasks, PRM constrains the evolution of cross-task prompts' parameters from Outer Prompt Granularity and Inner Prompt Granularity. Besides, we employ HRM to inherit old knowledge in the previously learned classifier heads to facilitate the cross-task prompts' generalization ability. Extensive experiments show the effectiveness of our method. The source codes will be available at \url{https://github.com/RAIAN08/PECTP}.

Chao Zhang, Hanxin Zhang, Atif Khan et al.

Importance: Lower-resource areas in Africa and Asia face a unique set of healthcare challenges: the dual high burden of communicable and non-communicable diseases; a paucity of highly trained primary healthcare providers in both rural and densely populated urban areas; and a lack of reliable, inexpensive internet connections. Objective: To address these challenges, we designed an artificial intelligence assistant to help primary healthcare providers in lower-resource areas document demographic and medical sign/symptom data and to record and share diagnostic data in real-time with a centralized database. Design: We trained our system using multiple data sets, including US-based electronic medical records (EMRs) and open-source medical literature and developed an adaptive, general medical assistant system based on machine learning algorithms. Main outcomes and Measure: The application collects basic information from patients and provides primary care providers with diagnoses and prescriptions suggestions. The application is unique from existing systems in that it covers a wide range of common diseases, signs, and medication typical in lower-resource countries; the application works with or without an active internet connection. Results: We have built and implemented an adaptive learning system that assists trained primary care professionals by means of an Android smartphone application, which interacts with a central database and collects real-time data. The application has been tested by dozens of primary care providers. Conclusions and Relevance: Our application would provide primary healthcare providers in lower-resource areas with a tool that enables faster and more accurate documentation of medical encounters. This application could be leveraged to automatically populate local or national EMR systems.

Chao Zhang, Sthitie Bom

With the proliferation of IoT devices, the distributed control systems are now capturing and processing more sensors at higher frequency than ever before. These new data, due to their volume and novelty, cannot be effectively consumed without the help of data-driven techniques. Deep learning is emerging as a promising technique to analyze these data, particularly in soft sensor modeling. The strong representational capabilities of complex data and the flexibility it offers from an architectural perspective make it a topic of active applied research in industrial settings. However, the successful applications of deep learning in soft sensing are still not widely integrated in factory control systems, because most of the research on soft sensing do not have access to large scale industrial data which are varied, noisy and incomplete. The results published in most research papers are therefore not easily reproduced when applied to the variety of data in industrial settings. Here we provide manufacturing data sets that are much larger and more complex than public open soft sensor data. Moreover, the data sets are from Seagate factories on active service with only necessary anonymization, so that they reflect the complex and noisy nature of real-world data. We introduce a variance weighted multi-headed auto-encoder classification model that fits well into the high-dimensional and highly imbalanced data. Besides the use of weighting or sampling methods to handle the highly imbalanced data, the model also simultaneously predicts multiple outputs by exploiting output-supervised representation learning and multi-task weighting.