arXiv subjects

Huamin Qu

Publications and source records attributed to Huamin Qu.

202 records · Page 12Linked to original sources

arXiv2017

Understanding Hidden Memories of Recurrent Neural Networks

Recurrent neural networks (RNNs) have been successfully applied to various natural language processing (NLP) tasks and achieved better results than conventional methods. However, the lack of understanding of the mechanisms behind their effectiveness limits further improvements on their architectures. In this paper, we present a visual analytics method for understanding and comparing RNN models for NLP tasks. We propose a technique to explain the function of individual hidden state units based on their expected response to input texts. We then co-cluster hidden state units and words based on the expected response and visualize co-clustering results as memory chips and word clouds to provide more structured knowledge on RNNs' hidden states. We also propose a glyph-based sequence visualization based on aggregate information to analyze the behavior of an RNN's hidden state at the sentence-level. The usability and effectiveness of our method are demonstrated through case studies and reviews from domain experts.

cs.CL↗

arXiv2017

CNNComparator: Comparative Analytics of Convolutional Neural Networks

Convolutional neural networks (CNNs) are widely used in many image recognition tasks due to their extraordinary performance. However, training a good CNN model can still be a challenging task. In a training process, a CNN model typically learns a large number of parameters over time, which usually results in different performance. Often, it is difficult to explore the relationships between the learned parameters and the model performance due to a large number of parameters and different random initializations. In this paper, we present a visual analytics approach to compare two different snapshots of a trained CNN model taken after different numbers of epochs, so as to provide some insight into the design or the training of a better CNN model. Our system compares snapshots by exploring the differences in operation parameters and the corresponding blob data at different levels. A case study has been conducted to demonstrate the effectiveness of our system.

cs.LG↗

arXiv2014

Previous R&D of vibrating wire alignment technique for HEPS

The alignment tolerance of multipoles on a girder is better than 30um in the storage ring of High Energy Photon Source HEPS which will be the next project at IHEP Institute of High Energy Physics. This is difficult to meet the precision only using the traditional optical survey method. In order to achieve this goal, vibrating wire alignment technique with high precision and sensitivity is considered to be used in this project. This paper presents some previous research works about theory, scheme design and achievements.

physics.acc-ph↗

arXiv2008

The beam energy calibration system for the BEPC-II collider

This document contains a proposal of the BEPC-II collider beam energy calibration system (IHEP, Beijing). The system is based on Compton backscattering of carbon dioxide laser radiation, producing a beam of high energy photons. Their energy spectrum is then accurately measured by HPGe detector. The high-energy spectrum edge will allow to determine the average electron or positron beam energy with relative accuracy about 3x10^-5.

physics.acc-ph↗