دانلود و نمایش مقالات مرتبط با معماری عصبی::صفحه 1
دانلود بهترین مقالات isi همراه با ترجمه فارسی 2

با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد). 

نتیجه جستجو - معماری عصبی

تعداد مقالات یافته شده: 6
ردیف عنوان نوع
1 Unsupervised foveal vision neural architecture with top-down attention
معماری عصبی چشم انداز بدون نظارت با توجه از بالا به پایین-2021
Deep learning architectures are an extremely powerful tool for recognizing and classifying images. However, they require supervised learning and normally work on vectors of the size of image pixels and produce the best results when trained on millions of object images. To help mitigate these issues, we propose an end-to-end architecture that fuses bottom-up saliency and top-down attention with an object recognition module to focus on relevant data and learn important features that can later be fine- tuned for a specific task, employing only unsupervised learning. In addition, by utilizing a virtual fovea that focuses on relevant portions of the data, the training speed can be greatly improved. We test the performance of the proposed Gamma saliency technique on the Toronto and CAT 2000 databases, and the foveated vision in the large Street View House Numbers (SVHN) database. The results with foveated vision show that Gamma saliency performs at the same level as the best alternative algorithms while being computationally faster. The results in SVHN show that our unsupervised cognitive architecture is comparable to fully supervised methods and that saliency also improves CNN performance if desired. Finally, we develop and test a top-down attention mechanism based on the Gamma saliency applied to the top layer of CNNs to facilitate scene understanding in multi-object cluttered images. We show that the extra information from top-down saliency is capable of speeding up the extraction of digits in the cluttered multidigit MNIST data set, corroborating the important role of top down attention.© 2021 Elsevier Ltd. All rights reserved.
Keywords: Unsupervised Learning | Foveal vision | Top-down saliency | Deep learning
مقاله انگلیسی
2 Using an AI creativity system to explore how aesthetic experiences are processed along the brain’s perceptual neural pathways
استفاده از یک سیستم خلاقیت هوش مصنوعی برای بررسی نحوه پردازش تجارب زیبایی شناختی در مسیرهای عصبی ادراکی مغز-2020
With the increased sophistication of AI techniques, the application of these systems has been expanding to ever newer fields. Increasingly, these systems are being used in modeling of human aesthetics and creativity, e.g. how humans create artworks and design products. Our lab has developed one such AI creativity deep learning system that can be used to create artworks in the form of images and videos. In this paper, we describe this system and its use in studying the human visual system and the formation of aesthetic experiences. Specifically, we show how time-based AI created media can be used to explore the nature of the dual-pathway neuro-architecture of the human visual system and how this relates to higher cognitive judgments such as aesthetic experiences that rely on these divergent information streams. We propose a theoretical framework for how the movement within percepts such as video clips, causes the engagement of reflexive attention and a subsequent focus on visual information that are primarily processed via the dorsal stream, thereby modulating aesthetic experiences that rely on information relayed via the ventral stream. We outline our recent study in support of our proposed framework, which serves as the first study that investigates the relationship between the two visual streams and aesthetic experiences.
Keywords: Neuroscience | Brain simulation | Artificial intelligence | Deep learning | Visual pathways | Neural pathways | Neuro-architecture | Aesthetics
مقاله انگلیسی
3 Progressive Operational Perceptrons with Memory
ادراک عملیاتی تصاعدی با حافظه-2020
Generalized Operational Perceptron (GOP) was proposed to generalize the linear neuron model used in the traditional Multilayer Perceptron (MLP) by mimicking the synaptic connections of biological neu- rons showing nonlinear neurochemical behaviours. Previously, Progressive Operational Perceptron (POP) was proposed to train a multilayer network of GOPs which is formed layer-wise in a progressive man- ner. While achieving superior learning performance over other types of networks, POP has a high com- putational complexity. In this work, we propose POPfast, an improved variant of POP that signicantly reduces the computational complexity of POP, thus accelerating the training time of GOP networks. In addition, we also propose major architectural modications of POPfast that can augment the progressive learning process of POP by incorporating an information preserving, linear projection path from the input to the output layer at each progressive step. The proposed extensions can be interpreted as a mechanism that provides direct information extracted from the previously learned layers to the network, hence the term “memory”. This allows the network to learn deeper architectures and better data representations. An extensive set of experiments in human action, object, facial identity and scene recognition problems demonstrates that the proposed algorithms can train GOP networks much faster than POPs while achiev- ing better performance compared to original POPs and other related algorithms.
Keywords: Generalized operational perceptron | Progressive learning | Neural architecture learning
مقاله انگلیسی
4 Surrogate-Assisted Evolutionary Search of Spiking Neural Architectures in Liquid State Machines
جستجوی تکاملی با کمک Surrogate از معماری عصبی اسپایک در ماشینهای حالت مایع-2020
Spiking neural networks (SNNs) are believed to be a powerful neural computation framework inspired by the vivo neurons. As a class of recurrent SNNs, liquid state machines (LSMs) are biologically more plausible models imitating the architecture and functions of the human brain for information processing. However, few LSM models can outperform conventional analogue neural networks for solving real-world classification or regression problems, which can mainly be attributed to the sensitivity of the training performance to the architecture of the reservoir and the parameters in the spiking neuron models. Most recently, many algorithms have been proposed for automated machine learning that aims to automatically design the architecture and parameters of deep neural networks without much human intervention. Although automated machine learning and neural architecture search have been extremely successful in conventional neural networks, little research on search for an optimal architecture and hyperparameters of LSMs has been reported. This work proposes on a surrogate-assisted evolutionary search method for optimization of the hyperparameters and neural architecture of the reservoir of LSMs using the covariance matrix adaptation evolution strategy (CMA-ES). For reducing the search space, the architecture of the LSM is encoded by a connectivity probability together with the hyperparameters in the spiking neuron models. To enhance the computational efficiency, a Gaussian process is adopted as the surrogate to assist the CMA-ES. The proposed GP-assisted CMA-ES is compared with the canonical CMA-ES and a Bayesian optimization algorithm on two popular datasets including image and action recognition. Our results confirm that the proposed algorithm is efficient and effective in optimizing the parameters and architecture of LSMs.
Keywords: Spiking neural network | Liquid state machine | Parameter and architecture search | Surrogate-assisted evolutionary search | Evolution strategy | Bayesian optimization | Gaussian process
مقاله انگلیسی
5 A reinforcement neural architecture search method for rolling bearing fault diagnosis
یک روش جستجوی معماری عصبی تقویت کننده برای تشخیص خطای احتمالی-2020
The fault diagnosis of rolling bearing has always been a research hotspot, and it is an urgent task to develop the effective method for rolling bearing fault identification. Most traditional methods cannot automatically build appropriately models for different datasets. In this paper, a neural network architecture automatic search method based on reinforcement learning is proposed for fault diagnosis of rolling bearings. The framework of proposed method contains of two components: a controller model and child models. The controller is recurrent neural network (RNN) and generates a series of actions, each action specifies a design choice to construct the child models for fault diagnosis. Then, the controller parameters are updated using the policy gradient method of reinforcement learning by maximizing the accuracy of the child models. The results confirm that the proposed method can realize the automatic design of neural network architecture and overcome the limitation of traditional methods.
Keywords: Fault diagnosis | Rolling bearing | Reinforcement learning | Neural architecture search method
مقاله انگلیسی
6 Generation of rhythmic hand movements in humanoid robots by a neural imitation learning architecture
تولید حرکات دست ریتمیک در ربات انسان نما بواسطه ی معماری عصبی آموزش تقلید-2017
This paper presents a two layer system for imitation learning in humanoid robots. The first layer of this system records complicated and rhythmic movement of the trainer using a motion capture device. It solves an inverse kinematic problem with the help of an adaptive Neuro-Fuzzy Inference system. Then it can achieve angles records of any joints involved in the desired motion. The trajectory is given as input to the systems second layer. The layer deals with extracting optimal parameters of the trajectories obtained from the first layer using a network of oscillator neurons and Particle Swarm Optimization algo- rithm. This system is capable to obtain any complex motion and rhythmic trajectory via first layer and learns rhythmic trajectories in the second layer then converge towards all these movements. Moreover, this two layer system is able to provide various features of a learner model, for instance resis- tance against perturbations, modulation of trajectories amplitude and frequency. The simulation results of the learning system is performed in the robot simulator WEBOTS linked with MATLAB software. Practical implementation on an NAO robot demonstrate that the robot has learned desired motion with high accuracy. These results show that proposed system in this paper produces high convergence rate and low test error.© 2016 Published by Elsevier B.V.
Keywords:Imitation learning | Neural networks | Central pattern generator
مقاله انگلیسی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی
logo-samandehi
بازدید امروز: 5986 :::::::: بازدید دیروز: 0 :::::::: بازدید کل: 5986 :::::::: افراد آنلاین: 72