東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Indirect Training Algorithms for Spi...

Zhang, Xu.

FindBook

Google Book

Amazon

博客來

Indirect Training Algorithms for Spiking Neural Networks based on Spiking Timing Dependent Plasticity and Their Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Indirect Training Algorithms for Spiking Neural Networks based on Spiking Timing Dependent Plasticity and Their Applications./
作者:	Zhang, Xu.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	151 p.
附註:	Source: Dissertation Abstracts International, Volume: 78-07(E), Section: B.
Contained By:	Dissertation Abstracts International78-07B(E).
標題:	Artificial intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10242034
ISBN:	9781369614084

Indirect Training Algorithms for Spiking Neural Networks based on Spiking Timing Dependent Plasticity and Their Applications.
Zhang, Xu.

Indirect Training Algorithms for Spiking Neural Networks based on Spiking Timing Dependent Plasticity and Their Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 151 p.

Source: Dissertation Abstracts International, Volume: 78-07(E), Section: B.

Thesis (Ph.D.)--Duke University, 2017.

Spiking neural networks have been used to investigate the mechanisms of processing in biological neural circuits or to propose hypotheses that can be tested in experiments. Because of their biological plausibility and event-based information trans- mission, Spiking Neural Networks (SNNs) have suggested as alternatives to Artificial Neural Networks for pattern recognition, classification and function approximation problems with fewer neurons. In machine learning, SNNs has been shown to be able to solve pattern and robotic control. For SNNs to be used for such problems, they must incorporate some mechanism for learning. Current methods to train SNNs use learning algorithms which adjust the synaptic weights according to an update rule. In most cases the weights are modified directly. In potential applications such as driving plasticity in neural culture (in-vitro) and training neuromorphic chips the directly manipulation of synaptic weights is not possible. Therefore, indirect algorithms, which cause the SNNs to learn based on some biological learning mechanisms using stimulation of neurons over significant advantages over the existing algorithm for these real world applications.

ISBN: 9781369614084Subjects--Topical Terms:

516317
Artificial intelligence.

Indirect Training Algorithms for Spiking Neural Networks based on Spiking Timing Dependent Plasticity and Their Applications.
LDR:04416nmm a2200325 4500 001 2122563
005 20170922124926.5
008 180830s2017 ||||||||||||||||| ||eng d
020 $a 9781369614084
035 $a (MiAaPQ)AAI10242034
035 $a AAI10242034
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Xu. $3 1020737
245 1 0 $a Indirect Training Algorithms for Spiking Neural Networks based on Spiking Timing Dependent Plasticity and Their Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 151 p.
500 $a Source: Dissertation Abstracts International, Volume: 78-07(E), Section: B.
500 $a Adviser: Craig S. Henriquez.
502 $a Thesis (Ph.D.)--Duke University, 2017.
520 $a Spiking neural networks have been used to investigate the mechanisms of processing in biological neural circuits or to propose hypotheses that can be tested in experiments. Because of their biological plausibility and event-based information trans- mission, Spiking Neural Networks (SNNs) have suggested as alternatives to Artificial Neural Networks for pattern recognition, classification and function approximation problems with fewer neurons. In machine learning, SNNs has been shown to be able to solve pattern and robotic control. For SNNs to be used for such problems, they must incorporate some mechanism for learning. Current methods to train SNNs use learning algorithms which adjust the synaptic weights according to an update rule. In most cases the weights are modified directly. In potential applications such as driving plasticity in neural culture (in-vitro) and training neuromorphic chips the directly manipulation of synaptic weights is not possible. Therefore, indirect algorithms, which cause the SNNs to learn based on some biological learning mechanisms using stimulation of neurons over significant advantages over the existing algorithm for these real world applications.
520 $a Indirect algorithms train the neural network by using external stimuli to modulate the synaptic strengths of a neural network according to synapses intrinsic mechanisms for plasticity. The training algorithms have been demonstrated in both Integrate and Fire neurons and more biologically realistic neural networks. In this thesis, four indirect methods to drive the synaptic weights to its desired value in a network through Spike Time Dependent Plasticity (STDP) are developed: Indirect Perturbation, In- direct Stochastic Gradient, Indirect ReSuMe, and Indirect Training with Supervised Teaching Signals. These algorithms are used to solve the temporal and spatial input- output mapping problem using temporal coding. The other type of problem is to mapping input output ring rates using rate coding.
520 $a To test the algorithms, SNNs are used to control both virtual and real world robots. For the real world robots with SNNs, known and Neurorobots, two types of robot localization techniques are used: Optitrack, using ceiling mounted cameras and onboard markers, and embedded cameras. Both small and large SNNs with biologically realistic neurons are used to drive the neurorobots are modeled with input coming from Optitrack or the cameras with GPU accelerated SNN simulator. The results show that the indirect perturbation and indirect stochastic gradient algorithms can train an SNN to control the robot to nd targets and avoid obstacles even in the presence of sensor noise. The results also show that indirect training with supervised training signals algorithm can train a feedforward network with 1000s of neurons to process and output the correct movement commands to localize a target using from real time images captured from an embedded camera. Finally. an indirect version of the Remote Supervised Method (ReSuMe) algorithm was developed using a more biologically realistic form of Spike-Timing Dependent Plasticity to produce a specific temporal pattern of spiking from a group of neurons. The indirect algorithms developed in this thesis may eventually allow the ability to train in vitro and in vivo biological circuits to perform specific tasks using patterns of electrical or light stimulation.
590 $a School code: 0066.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Neurosciences. $3 588700
650 4 $a Robotics. $3 519753
690 $a 0800
690 $a 0317
690 $a 0771
710 2 $a Duke University. $b Mechanical Engineering and Materials Science. $3 1030656
773 0 $t Dissertation Abstracts International $g 78-07B(E).
790 $a 0066
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10242034