54,021 Hits in 3.4 sec

From Brain Science to Artificial Intelligence

Jingtao Fan, Lu Fang, Jiamin Wu, Yuchen Guo, Qionghai Dai
2020 Engineering  
Reviewing the history of the development of artificial intelligence (AI) clearly reveals that brain science has resulted in breakthroughs in AI, such as deep learning.  ...  The first steps toward this goal are to explore the secrets of brain science by studying new brain-imaging technology; to establish a dynamic connection diagram of the brain; and to integrate neuroscience  ...  Compliance with ethics guidelines Jingtao Fan, Lu Fang, Jiamin Wu, Yuchen Guo, and Qionghai Dai declare that they have no conflicts of interest or financial conflicts to disclose.  ... 
doi:10.1016/j.eng.2019.11.012 fatcat:qqw7gh5gpbaidhaxado4iw6ipq

How do artificial neural networks lead to developing an optimization method?

Sadollah Ali
2020 Trends in Computer Science and Information Technology  
Abstract This concise paper explains the inspiration of AI particularly artifi cial neural networks (ANNs) for developing new metaheuristics.  ...  Many applications and improvement have been inspired using the ANNs. Question of how ANNs inspire a new optimizer is underlined in its unique structure.  ...  Artifi cial Neural Networks (ANNs) Artifi cial neural networks (ANNs) are computing structures inspired by biological neural network structure and/or functional aspects.  ... 
doi:10.17352/tcsit.000026 fatcat:4myirtesunb4jniwapxxwwhw2u

Towards efficient end-to-end speech recognition with biologically-inspired neural networks [article]

Thomas Bohnstingl, Ayush Garg, Stanisław Woźniak, George Saon, Evangelos Eleftheriou, Angeliki Pantazi
2021 arXiv   pre-print
On the other hand, the current developments in biologically-inspired ASR models, based on spiking neural networks (SNNs), lag behind in terms of accuracy and focus primarily on small scale applications  ...  In this work, we revisit the incorporation of biologically-plausible models into deep learning and we substantially enhance their capabilities, by taking inspiration from the diverse neural and synaptic  ...  Acknowledgment We thank the Neuromorphic Computing and I/O Links group at IBM Research -Zurich for fruitful discussions and comments.  ... 
arXiv:2110.02743v2 fatcat:pfih5epzu5bfderva67elofhzy

Are skip connections necessary for biologically plausible learning rules? [article]

Daniel Jiwoong Im, Rutuja Patil, Kristin Branson
2019 arXiv   pre-print
Backpropagation is the workhorse of deep learning, however, several other biologically-motivated learning rules have been introduced, such as random feedback alignment and difference target propagation  ...  In this paper, we show that biologically-motivated learning rules with skip connections between intermediate layers can perform as well as backpropagation on the MNIST dataset and are robust to various  ...  Such concerns have inspired researchers to develop biologically-motivated learning rules 1 while trying to attain the performance of artificial neural networks.  ... 
arXiv:2001.01647v1 fatcat:5u267moxwnhbhhhgi7lrk7ooxu

Bio-inspired intelligence with applications to robotics: a survey

Junfei Li, Zhe Xu, Danjie Zhu, Kevin Dong, Tao Yan, Zhu Zeng, Simon X. Yang
2021 Intelligence & Robotics  
The bio-inspired neural network has been widely used in real-time collision-free navigation and cooperation without any learning procedures, global cost functions, and prior knowledge of the dynamic environment  ...  A bio-inspired neural network framework, in which neurons are characterized by the neurodynamics models, is discussed for mobile robots, cleaning robots, and underwater robots.  ...  However, the learning process of the adaptive neural network can reduce the real-time performance, which is the superiority of the bio-inspired neural network.  ... 
doi:10.20517/ir.2021.08 fatcat:zlctzg5sibhqdcieg3rfqhbgdq

A Neural Network-Based Approach for Trajectory Planning in Robot–Human Handover Tasks

Elena De Momi, Laurens Kranendonk, Marta Valenti, Nima Enayati, Giancarlo Ferrigno
2016 Frontiers in Robotics and AI  
After the design and training of the neural controller for motion planning, we checked the objective characteristics of the achieved biologically inspired motion as functional minimization (minimum jerk  ...  a trajectory planning system based on an artificial neural network architecture trained on human actions.  ...  This paper presents a neural controller approach generating "biologically inspired" type trajectories for a robotic scrub nurse in order to increase the effectiveness of human robot interaction, as per  ... 
doi:10.3389/frobt.2016.00034 fatcat:5pjotm4k4rgu3fshj4iejnntai

A Review of Heuristic Global Optimization Based Artificial Neural Network Training Approahes

D. Geraldine Bessie Amali, Dinakaran M.
2017 IAES International Journal of Artificial Intelligence (IJ-AI)  
The training algorithms are compared in terms of the learning rate, convergence speed and accuracy of the output produced by the neural network.  ...  Training a neural network involves minimizing the mean square error between the target and network output. The error surface is nonconvex and highly multimodal.  ...  INTRODUCTION Artificial Neural Network (ANN) is a mathematical model of the biological nervous system.  ... 
doi:10.11591/ijai.v6.i1.pp26-32 fatcat:mkalw6ikzbh45fteocs56nuz4i

Convolutional Neural Network with Biologically Inspired Retinal Structure

Jonghong Kim, O. Sangjun, Yoonnyun Kim, Minho Lee
2016 Procedia Computer Science  
In this paper, we propose a new Convolutional Neural Network (CNN) with biologically inspired retinal structure and ON/OFF Rectified Linear Unit (ON/OFF ReLU).  ...  improves the performance of conventional CNN.  ...  neural network was inspired by simple cells and complex cells in the human visual cortex, a key obstacle in training deep neural networks, the vanishing gradient problem, has been alleviated through a  ... 
doi:10.1016/j.procs.2016.07.418 fatcat:7nwfqvmo6fcqnln44smbuqlxxm

Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects [article]

Bing Wei, Yudi Zhao, Kuangrong Hao, Lei Gao
2021 arXiv   pre-print
Then, some points of view about the prospects of the visual perception computational models are presented.  ...  Computational models inspired by visual perception have the characteristics of complexity and diversity, as they come from many subjects such as cognition science, information science, and artificial intelligence  ...  They found that the deep neural network reproduced key behavioral results, including increasing specificity with higher task precision.  ... 
arXiv:2109.03391v1 fatcat:xtgda2x6azd2laun45tqfj77gi

Path Planning for Swarm AUV Visiting Communication Node [chapter]

Chao Geng, Guannan Li, Hongli Xu
2019 Lecture Notes in Computer Science  
This paper proposes a method for path planning of an underwater robot swarm. The method is based on biological inspired neural network to plan path between robots and communication nodes.  ...  Then build biologically inspired neural network based on the grid map. The node attracts the robots and the obstacles reject the robots through neural activity.  ...  Model of Biological Inspiration Neural Network A biological neural system using electrical circuit elements was first proposed by Hodgkin and Huxley.  ... 
doi:10.1007/978-3-030-27535-8_22 fatcat:et6fmsbn7jhbxeboo72dcr2t74

Deep Connectomics Networks: Neural Network Architectures Inspired by Neuronal Networks [article]

Nicholas Roberts, Dian Ang Yap, Vinay Uday Prabhu
2019 arXiv   pre-print
of biological neural networks.  ...  The architectures of deep neural networks (DNNs) do not resemble their biological counterparts in the topological sense.  ...  However, the field of deep neural networks, with all its neuro-biologically inspired building blocks, has mostly left the topology story out. 1 Curiously, in the Cambrian explosion of neural network architectures  ... 
arXiv:1912.08986v1 fatcat:aiee7np72zh2dh5iekshn7jrk4

Bio-Inspired Stochastic Neural Networks for Nanoelectronics

Eelco Rouw
2002 AIP Conference Proceedings  
Therefore a new design of neuraI networks using biological principles, because of the similarity with nanoelectronics is necessary.  ...  However, conventional neuraI networks are not suitable due to the topological requirements of nanoelectronics.  ...  For the artificial bio-inspired neural networks the key element consists of the adaptive synapse.  ... 
doi:10.1063/1.1503725 fatcat:57737hcwkbfwtkr7vz4j67c52q

Quantifying the Brain Predictivity of Artificial Neural Networks with Nonlinear Response Mapping [article]

Aditi Anand, Sanchari Sen, Kaushik Roy
2020 bioRxiv   pre-print
Quantifying the similarity between artificial neural networks (ANNs) and their biological counterparts is an important step towards building more brain-like artificial intelligence systems.  ...  Recent efforts in this direction use neural predictivity, or the ability to predict the responses of a biological brain given the information in an ANN (such as its internal activations), when both are  ...  The authors gratefully acknowledge Martin Schrimpf and James DiCarlo from the Department of Brain and Cognitive Sciences at the Massachusetts Institute of Technology for providing them with the neural  ... 
doi:10.1101/2020.09.27.315747 fatcat:3g34dmio3rckjleksyn5t3o7le

A Fast Adaptive Block-matching Motion Estimation Algorithm

Youwei Yuan, Weilei Xu, Yong Li, Lamei Yan
2014 International Journal of Multimedia and Ubiquitous Engineering  
The main goal is to bridge the gap between algorithmic and biological vision by suggesting a bio-inspired motion estimation model based on neural network.  ...  In this work, we have developed a new bio-inspired neural network algorithms for blockbased motion estimation.  ...  Acknowledgments The work was supported by NSFC (Grant No. 61272032) and also supported by the nature science foundation of Zhejiang province (No. Y6090312).  ... 
doi:10.14257/ijmue.2014.9.4.10 fatcat:rh2mz2qn25gpthhcbmgksyj3zm

Modeling and Simulation of Spiking Neural Networks with Resistive Switching Synapses [chapter]

Valerio Milo
2019 SpringerBriefs in Applied Sciences and Technology  
Then, the application of RRAM synapses in spiking neural networks to achieve neuromorphic tasks such as on-line learning of images and associative learning is addressed.  ...  Artificial intelligence (AI) has recently reached excellent achievements in the implementation of human brain cognitive functions such as learning, recognition and inference by running intensively neural  ...  from how the human brain processes information via biological neural networks [11] .  ... 
doi:10.1007/978-3-030-32094-2_4 fatcat:ysddkppk5belfdasqrzlrws42y
« Previous Showing results 1 — 15 out of 54,021 results