Results 61 to 70 of about 20,311 (188)

Evolutionary computing in operational research for two-layer neural networks [PDF]

, 2017
Considering the non-linear characteristics of the activation functions, the entire task is multidimensional and non-linear with a multimodal target function.
Płaczek, S.
core  

Artificial intelligence in pharmaceutical product formulation: neural computing [PDF]

Chemical Industry and Chemical Engineering Quarterly, 2009
The properties of a formulation are determined not only by the ratios in which the ingredients are combined but also by the processing conditions. Although the relationships between the ingredient levels, processing conditions, and product performance ...
Svetlana Ibrić, Jelena Petrović, Jelena Parojčić, Zorica Djurić   +3 more
doaj  

Joint Hardware-Workload Co-Optimization for In-Memory Computing Accelerators

IEEE Access
Software-hardware co-design is essential for optimizing in-memory computing (IMC) hardware accelerators for neural networks. However, most existing optimization frameworks target a single workload, leading to highly specialized hardware designs that do ...
Olga Krestinskaya, Mohammed E. Fouda, Ahmed M. Eltawil, Khaled N. Salama   +3 more
doaj   +1 more source

Evolutionary Design of Convolutional Neural Networks

, 2021
The aim of this Master's thesis is to describe basic technics of evolutionary computing, convolutional neural networks (CNN), and automated design of neural networks using neuroevolution ( NAS - Neural Architecture Search ).
Pristaš, Ján
core  

Multi-Agent Reinforcement Learning in Games: Research and Applications

Biomimetics
Biological systems, ranging from ant colonies to neural ecosystems, exhibit remarkable self-organizing intelligence. Inspired by these phenomena, this study investigates how bio-inspired computing principles can bridge game-theoretic rationality and ...
Haiyang Li, Ping Yang, Weidong Liu, Shaoqiang Yan, Xinyi Zhang, Donglin Zhu   +5 more
doaj   +1 more source

Hybrid of Evolutionary and Swarm Intelligence Algorithms for Prosody Modeling in Natural Speech Synthesis

International Journal of Information and Communication Technology Research, 2016
To reduce the number of input features to a prosody generator in natural speech synthesis application, a hybrid of an evolutionary algorithm and a swarm intelligence-based algorithm is used for feature selection (FS) in this study.
Mansour Sheikhan
doaj  

Enhancing Neural Architecture Search Using Transfer Learning and Dynamic Search Spaces for Global Horizontal Irradiance Prediction

Forecasting
The neural architecture search technique is used to automate the engineering of neural network models. Several studies have applied this approach, mainly in the fields of image processing and natural language processing.
Inoussa Legrene, Tony Wong, Louis-A. Dessaint   +2 more
doaj   +1 more source

Evolutionary Computing based an Efficient and Cost Effective Software Defect Prediction System [PDF]

, 2015
The earlier defect prediction and fault removal can play a vital role in ensuring software reliability and quality of service In this paper Hybrid Evolutionary computing based Neural Network HENN based software defect prediction model has been ...
Racharla Suresh Kumar, Prof. Bachala Sathyanarayana   +1 more
core  

Reservoir Computing in an Evolutionary Neuromorphic Framework [PDF]

, 2019
Neuromorphic computing is an emerging hardware paradigm for doing non-traditional computing. It has advantages over typical von Neumann systems in a myriad of different situations.
Reynolds, John J.
core  

Research Progress on Drosophila Electron Microscopy Connectome Database and Functional Analysis of Related Neural Circuits

Shiyan dongwu yu bijiao yixue
In recent years, research on the electron microscopy connectome of Drosophila melanogaster has achieved major breakthroughs, providing neural circuit maps with synaptic resolution across the whole brain.
DENG Xianming, WANG Fei
doaj   +1 more source