Results 51 to 60 of about 49,141 (264)

Neural architectures for gender detection and speaker identification

Cogent Engineering, 2020
In this paper, we investigate two neural architecture for gender detection and speaker identification tasks by utilizing Mel-frequency cepstral coefficients (MFCC) features which do not cover the voice related characteristics.
Orken Mamyrbayev, Alymzhan Toleu, Gulmira Tolegen, Nurbapa Mekebayev   +3 more
doaj   +1 more source

Organic Materials of Tomorrow: Horizons of Artificial Intelligence

Advanced Materials, EarlyView.
This review examines machine learning techniques accelerating the discovery of organic semiconductors by linking molecular structure to properties. Key methods include graph neural networks, generative models, and active learning. Applications to organic photovoltaics demonstrate practical impact.
Harold Mena, J. Terence Blaskovits, Kun‐Han Lin, Denis Andrienko   +3 more
wiley   +1 more source

Building MLP networks by construction

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000
We introduce two new models which are obtained through the modification of the well known methods MLP and cascade correlation. These two methods differ fundamentally as they employ learning techniques and produce network architectures that are not directly comparable.
M. HAGENBUCHNER, MICHELI, ALESSIO, A. C. TSOI   +2 more
openaire   +3 more sources

Path‐Decoupled Cation‐Eutaxy III–V van der Waals Memristive Semiconductors for Mitigating the Neuromorphic Accuracy‐Energy Trade‐off

Advanced Materials, EarlyView.
Path‐decoupled III–V van der Waals memtransistors spatially separate ionic and electronic transport to overcome the conventional trade‐off between accuracy and energy in neuromorphic hardware. Mobile K+ ions in the vdW gaps set a wide conductance window, Gmax/Gmin, while gate‐tunable hole conduction lowers programming energy, enabling reliable ...
Jihong Bae, Ji Hoon Han, Taeyoung Kim, Jongbum Won, Seokmin Park, Gyu Won Kim, Sungsoon Kim, Hong Choi, Taehoon Kim, Hong‐Sub Lee, Jae‐Hyun Lee, Young Jin Choi, Jinwoo Cheon, Wooyoung Shim   +13 more
wiley   +1 more source

Noise‐Tunable Memristor Enabling Programmable Probabilistic Neurons for Frequency‐Selective Time‐Series Signal Encoding

Advanced Materials, EarlyView.
Memristors offer tunable resistance and intrinsic instability, making them promising tunable noise sources. We propose a spiking‐rate‐programmable probabilistic neuron using a Ru/TaOx/Pt memristor, where resistance‐dependent noise enables frequency‐selective encoding.
Do Hoon Kim, Seoeun Jang, Hakseung Rhee, Min Gu Lee, Daehee Kim, Taewook Go, Woon Hyung Cheong, Hanchan Song, Kyung Min Kim   +8 more
wiley   +1 more source

On‐Chip Photonic Neural Network Architectures

Advanced Optical Materials, EarlyView.
This review presents a comprehensive overview of on‐chip photonic neural network architectures, covering key photonic building blocks, representative network types, and emerging applications. Recent advances, implementation challenges, and future directions are examined, highlighting the potential of integrated photonics to enable ultrafast, energy ...
Seokjin Hong, Berkay Neseli, Seungyeon Cho, Seungsoo Lee, Yeonjun Kim, Seungyoon Choi, Hyo‐Hoon Park, Hamza Kurt   +7 more
wiley   +1 more source

DBDW: A Dual-Branch Database Workload Prediction Model

Journal of Applied Science and Engineering
Scalable cloud databases allow users to dynamically adjust computational resources based on business needs. However, most current elastic scaling techniques face challenges in making sound decisions due to complex workload variations. Achieving efficient
Chao Yang, Tiantian Liu, Fang Peng, Tianyou Zhu   +3 more
doaj   +1 more source

Mimetic Initialization of MLPs

CoRR
Mimetic initialization uses pretrained models as case studies of good initialization, using observations of structures in trained weights to inspire new, simple initialization techniques. So far, it has been applied only to spatial mixing layers, such convolutional, self-attention, and state space layers.
Asher Trockman, J. Zico Kolter
openaire   +2 more sources

Learning Highly Dynamic Skills Transition for Quadruped Jumping Through Constrained Space

Advanced Robotics Research, EarlyView.
A quadruped robot masters dynamic jumps through constrained spaces with animal‐inspired moves and intelligent vision control. This hierarchical learning approach combines imitation of biological agility with real‐time trajectory planning. Although legged animals are capable of performing explosive motions while traversing confined spaces, replicating ...
Zeren Luo, Jiahui Zhang, Yimin Han, Ji Ma, Minghao Lu, Ioannis Havoutis, Peng Lu   +6 more
wiley   +1 more source

Multilayer Perceptron Model with Feature Extraction for Potassium Deficiency Identification of Cocoa Plants

JOIV: International Journal on Informatics Visualization
The development of Multilayer Perceptron (MLP) models for networked learning systems heavily relies on the specific application case study and the accurate parameterization aligned with the chosen computer vision feature extraction models.
Basri Basri, Harli A Karim, Muhammad Assidiq, Muhammad Arafah, Fitria Rahmadani   +4 more
doaj   +1 more source