Results 91 to 100 of about 41,575 (296)
IET Computers & Digital Techniques, 2023 The intellectual properties (IP) protection of deep neural networks (DNN) models has raised many concerns in recent years. To date, most of the existing works use DNN watermarking to protect the IP of DNN models. However, the DNN watermarking methods can
Mingfu Xue +6 more
doaj +1 more source
sml911/Adversarial-DNN: First Release
, 2020 Cooper graduate research on generative adversaries in adversarial ...
Stephen
core +1 more source
Terahertz Channel Modeling, Estimation and Localization in RIS‐Assisted Systems
Advanced Electronic Materials, EarlyView.Reconfigurable intelligent surfaces have become a recent intensive research focus. Based on practical applications, channel strategies for RIS‐assisted terahertz wireless communication systems are categorized into three different types: channel modeling, channel estimation, and channel localization.
Hongjing Wang +9 more
wiley +1 more source
DNN Speaker Tracking with Embeddings
Res. Comput. Sci., 2020 In multi-speaker applications is common to have pre-computed models from enrolled speakers. Using these models to identify the instances in which these speakers intervene in a recording is the task of speaker tracking. In this paper, we propose a novel embedding-based speaker tracking method.
Carlos Rodrigo Castillo-Sanchez +2 more
openaire +2 more sources
Energy-Efficient DNN Training Processors on Micro-AI Systems
, 2022 Many edge/mobile devices are now able to utilize deep neural networks (DNNs) thanks to the development of mobile DNN accelerators. Mobile DNN accelerators overcame the problems of limited computing resources and battery capacity by realizing energy ...
Lee, Juhyoung +9 more
core +1 more source
Emerging Memory and Device Technologies for Hardware‐Accelerated Model Training and Inference
Advanced Electronic Materials, EarlyView.This review investigates the suitability of various emerging memory technologies as compute‐in‐memory hardware for artificial intelligence (AI) applications. Distinct requirements for training‐ and inference‐centric computing are discussed, spanning device physics, materials, and system integration.
Yoonho Cho +6 more
wiley +1 more source
ACCELERATING DNN INFERENCE AND TRAINING IN DISTRIBUTED SYSTEMS
, 2022 Deep Neural Network (DNN) models have been widely deployed in a variety of applications. To achieve better performance, DNN models become more and more complex, which introduces extremely long DNN training time.
Duan, Yubin
core +1 more source
On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification
Advanced Electronic Materials, EarlyView.ABSTRACT Reservoir computing (RC) is an emerging recurrent neural network architecture that has attracted growing attention for its low training cost and modest hardware requirements. Memristor‐based circuits are particularly promising for RC, as their intrinsic dynamics can reduce network size and parameter overhead in tasks such as time‐series ...
Rishona Daniels +4 more
wiley +1 more source
Ion‐Gating Reservoir Computing for Preprocessing‐Free Speech Recognition from Throat Vibrations
Advanced Electronic Materials, EarlyView.This work presents a throat‐mounted mechanoelectric sensor integrated with an ion‐gel/graphene reservoir device for on‐device speech recognition. The system converts raw biomechanical vibrations into rich nonlinear current dynamics, enabling efficient classification through a simple linear readout. The approach highlights a compact and tunable physical‐
Daiki Nishioka +5 more
wiley +1 more source
A Novel Tree Model-based DNN to Achieve a~High-Resolution DOA Estimation via Massive MIMO Receive Array [PDF]
RadioengineeringTo satisfy the high-resolution requirements of direction-of-arrival (DOA) estimation, conventional deep neural network (DNN)-based methods using grid idea need to significantly increase the number of output classifications and also produce a huge high ...
Y. Li, F. Shu, Y. Song, J. Wang
doaj