Results 141 to 150 of about 1,429,068 (340)

Convolutional neural network for dog breed recognition system

Adaptivni Sistemi Avtomatičnogo Upravlinnâ
The object of research is models of convolutional neural networks and datasets for training convolutional neural networks. The purpose of the study is to increase the efficiency of recognition of dog breeds using convolutional neural networks when ...
К. Хотінь, В. Шимкович, П. Кравець, А. Новацький, Л. Шимкович   +4 more
doaj   +1 more source

Large-Scale Video Classification with Convolutional Neural Networks

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014
A. Karpathy, G. Toderici, Sanketh Shetty, Thomas Leung, R. Sukthankar, Li Fei-Fei   +5 more
semanticscholar   +1 more source

Integration of Soft‐Robotics and Deep Learning to Assess the Coordinated Biosonar Emission and Reception Dynamics in Hipposiderid Bats

Advanced Robotics Research, EarlyView.
Combining a biomimetic soft‐robot with deep‐learning data analytics sheds light on a unique peripheral dynamics seen in the biosonar system of bats: Bats modulate their ultrasonic biosonar signals upon emission as well as reception with variable, yet highly coordinated motion patterns of their noseleaves and pinnae.
Shuxin Zhang, Ruihao Wang, Xiaoyan Yin, Luhui Yang, Rolf Müller   +4 more
wiley   +1 more source

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks [PDF]

, 2015
Marcel Simon, Erik Rodner
openalex   +1 more source

Flexible Sensor‐Based Human–Machine Interfaces with AI Integration for Medical Robotics

Advanced Robotics Research, EarlyView.
This review explores how flexible sensing technology and artificial intelligence (AI) significantly enhance human–machine interfaces in medical robotics. It highlights key sensing mechanisms, AI‐driven advancements, and applications in prosthetics, exoskeletons, and surgical robotics.
Yuxiao Wang, Zhipeng Jiang, Sun Hwa Kwon, Matthew Ibrahim, Alexander Dang, Lin Dong   +5 more
wiley   +1 more source

Some Improvements on Deep Convolutional Neural Network Based Image Classification

, 2013
Andrew Howard
openalex   +2 more sources

3D Elastomeric Kirigami for Passively Stretchable Fully Soft Vacuum‐Powered Artificial Muscles

Advanced Robotics Research, EarlyView.
The creation of purely soft, passively stretchable artificial muscles has long been a hot topic in robotics research. Here, we present a design approach involving the extension of 2D kirigami to 3D elastomeric kirigami structures. In a biomimetic demonstration of the human upper arm, this approach successfully simulated the driving mechanism ...
Tao Wang, Hongyuan Wang, Qian Liu, Xi Wang, Guoqiang Fu, Caijiang Lu, Bo Li, Jinhua Zhang, Hongying Zhang   +8 more
wiley   +1 more source

Liquid Metal Sensors for Soft Robots

Advanced Robotics Research, EarlyView.
This review thoroughly reviews liquid metal sensors in soft robots. Their unique material properties like high conductivity and good biocompatibility are analyzed. Working principles are classified, and applications in environmental perception, motion detection, and human—robot interaction are introduced.
Qi Zhang, Nan Li, Yujia Song, Chen Hua, Tangzhen Guan, Yibing Ma, Cai Cheng, Jing Liu   +7 more
wiley   +1 more source

Hybrid multi-objective evolutionary model compression with convolutional neural networks

Results in Engineering
Deep learning has been utilized in the fields of image processing, natural language processing and speech recognition. For improving the structure of deep learning, how to compress Convolutional Neural Networks has become a major focus topic.
Shuhan Zhang, Yanjie Gao
doaj  

Estimating Phoneme Class Conditional Probabilities from Raw Speech Signal using Convolutional Neural Networks

, 2013
Dimitri Palaz, Ronan Collobert, Mathew Magimai. -Doss   +2 more
openalex   +2 more sources