Search Results for author:
Found 12 papers, 2 papers with code
LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference
While existing works mostly fix the model precision during the whole training process, a few pioneering works have shown that dynamic precision schedules help DNNs converge to a better accuracy while leading to a lower training cost than their static precision training counterparts.
MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation
ViTs are often too computationally expensive to be fitted onto real-world resource-constrained devices, due to (1) their quadratically increased complexity with the number of input tokens and (2) their overparameterized self-attention heads and model depth.
Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage.
O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed
The recent breakthroughs and prohibitive complexities of Deep Neural Networks (DNNs) have excited extensive interest in domain-specific DNN accelerators, among which optical DNN accelerators are particularly promising thanks to their unprecedented potential of achieving superior performance-per-watt.
A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning
Driven by the explosive interest in applying deep reinforcement learning (DRL) agents to numerous real-time control and decision-making applications, there has been a growing demand to deploy DRL agents to empower daily-life intelligent devices, while the prohibitive complexity of DRL stands at odds with limited on-device resources.
InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices.
HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark
To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).
HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark
To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance (e. g., energy cost and latency) of all the networks in the search space of both NAS-Bench-201 and FBNet, considering six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).
Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
We therefore propose an Auto-Agent-Distiller (A2D) framework, which to our best knowledge is the first neural architecture search (NAS) applied to DRL to automatically search for the optimal DRL agents for various tasks that optimize both the test scores and efficiency.
Kernel Quantization for Efficient Network Compression
Thus, KQ can represent the weight tensor in the convolution layer with low-bit indexes and a kernel codebook with limited size, which enables KQ to achieve significant compression ratio.
Exploiting Partially Annotated Data in Temporal Relation Extraction
As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.
Exploiting Partially Annotated Data for Temporal Relation Extraction
As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.
