Learn More
We propose a novel deep network structure called " Network In Network " (NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. Instead, we build micro neural networks with more complex structures to abstract(More)
People frequently write messages to themselves. These informal, hurried personal jottings serve as temporary storage for notable information as well as reminders for future action. Many mobile technologies have been designed specifically to support this ubiquitous behavior; however, adoption has been universally problematic. Despite its clear utility, the(More)
MXNet is a multi-language machine learning (ML) library to ease the development of ML algorithms, especially for deep neural networks. Embedded in the host language, it blends declarative symbolic expression with imperative tensor computation. It offers auto differentiation to derive gradients. MXNet is computation and memory efficient and runs on various(More)
In this paper, we introduce a novel deep learning framework, termed Purine. In Purine, a deep network is expressed as a bipartite graph (bi-graph), which is composed of interconnected operators and data tensors. With the bi-graph abstraction, networks are easily solvable with event-driven task dispatcher. We then demonstrate that different parallelism(More)
OBJECTIVE To summarize the experience with salvage liver transplantation (SLT) for patients with recurrent hepatocellular carcinoma (HCC) after primary hepatic resection in a single center. METHODS A total of 376 adult patients with HCC underwent orthotopic liver transplantation (OLT) at Organ Transplantation Center, the First Affiliated Hospital of Sun(More)
—To effectively deploy wireless sensor networks (WSNs) for monitoring and assessing the condition of tunnels, a Propagation Path Loss (PL) Model, which describes the power loss versus distance between the transmitter and the receiver for the tunnel environment is required. For most of the existing propagation measurements that have been conducted in(More)
Developing more effective and efficient Chinese character input methods has the potential to help Chinese mobile phone users (currently 320 millions) input text messages. iTAP(R) supports input based on the writing structure of Chinese characters. Current keypad graphics include three items: digits (0-9), letters (A-Z), and symbols that represent the(More)