Diagnose Like a Radiologist : Hybrid Neuro-Probabilistic Reasoning for Attrib…

During clinical practice, radiologists often use attributes, e.g., morphological and appearance characteristics of a lesion, to aid disease diagnosis. Effectively modeling attributes as well as all…

Improved Algorithm for Phase Generation Carrier to Eliminate the Influence of…

Traditional phase generation carrier technology requires to control the modulation depth at an optimal value for accurate demodulation. In this paper, we proposed an algorithm to directly eliminate…

Progressive Tandem Learning for Pattern Recognition With Deep Spiking Neural …

Spiking neural networks (SNNs) have shown clear advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency, due to their event-driven nature and…

Memristor Parallel Computing for a Matrix-Friendly Genetic Algorithm

Matrix operation is easy to be paralleled by hardware, and the memristor network can realize a parallel matrix computing model with in-memory computing. This article proposes a matrix-friendly gene…

Dynamic Optimal Reinsurance and Dividend Payout in Finite Time Horizon

This paper studies a dynamic optimal reinsurance and dividend-payout problem for an insurance company in a finite time horizon. The goal of the company is to maximize the expected cumulative discou…

OANet : Learning Two-View Correspondences and Geometry Using Order-Aware Network

Establishing correct correspondences between two images should consider both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we propo…

Depth Selection for Deep ReLU Nets in Feature Extraction and Generalization

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advanta…

Interpretable CNNs for Object Classification

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes fea…

A 1.4-kW Mode-Controllable Fiber Laser System

We demonstrated a mode-controllable fiber laser system with output power of 1.4 kW level. The system consists of a kilowatt-scale master oscillator power amplifier and an active feedback control sy…

Performance Enhanced 256-QAM BIPCM-DMT System Enabled by CAZAC Precoding