A Non-fully-Connected Spiking Neural Network with STDP for Solving a Classification Task

Inspire by nature world mode, a activation function is proposed. It is absolute function.Through test on mnist dataset and fully-connected neural network and convolutional neural network, some conclusions are put forward. The line of accuracy of absolute function is shaked around the training accuracy that is different from the line of accuracy of relu and leaky relu. The absolute function can keep the negative parts as equal as the positive parts, so the individualization is more active than relu and leaky relu function. The absolute function is less likely to be over-fitting. Through teat on mnist and autoencoder, It is that the leaky relu function can do classification task well, while the absolute function can do generation task well. Because the classification task need more universality and generation task need more individualization. The pleasure irritation and painful irritation is not only the magnitude differences, but also the sign differences, so the negative parts should keep as a part.Stimulation which happens frequently is low value, it is showed around zero in figure 1 . Stimulation which happens accidentally is high value, it is showed far away from zero in figure 1. So the high value is the big stimulation, which is individualization.

Download Full-text

Fully-connected single-layer STT-MTJ-based spiking neural network under process variability

2017 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH) ◽

10.1109/nanoarch.2017.8053727 ◽

2017 ◽

Cited By ~ 4

Author(s):

Elena Ioana Vatajelu ◽

Lorena Anghel

Keyword(s):

Neural Network ◽

Single Layer ◽

Spiking Neural Network ◽

Process Variability ◽

Fully Connected

Download Full-text

Activation Function: Absolute Function, One Function Behaves more Individualized

10.36227/techrxiv.17639525 ◽

2021 ◽

Author(s):

Jinxin Wei ◽

Zhe Hou

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Activation Function ◽

Classification Task ◽

Generation Task ◽

The Absolute ◽

Fully Connected ◽

Mode A

Inspire by nature world mode, a activation function is proposed. It is absolute function.Through test on mnist dataset and fully-connected neural network and convolutional neural network, some conclusions are put forward. The line of accuracy of absolute function is shaked around the training accuracy that is different from the line of accuracy of relu and leaky relu. The absolute function can keep the negative parts as equal as the positive parts, so the individualization is more active than relu and leaky relu function. The absolute function is less likely to be over-fitting. Through teat on mnist and autoencoder, It is that the leaky relu function can do classification task well, while the absolute function can do generation task well. Because the classification task need more universality and generation task need more individualization. The pleasure irritation and painful irritation is not only the magnitude differences, but also the sign differences, so the negative parts should keep as a part.Stimulation which happens frequently is low value, it is showed around zero in figure 1 . Stimulation which happens accidentally is high value, it is showed far away from zero in figure 1. So the high value is the big stimulation, which is individualization.

Download Full-text

TESTING OF INFORMATION CONDENSATION IN A MODEL REVERBERATING SPIKING NEURAL NETWORK

International Journal of Neural Systems ◽

10.1142/s0129065711002742 ◽

2011 ◽

Vol 21 (03) ◽

pp. 187-198 ◽

Cited By ~ 20

Author(s):

ALEXANDER VIDYBIDA

Keyword(s):

Neural Network ◽

External World ◽

Spike Trains ◽

Condensation Process ◽

Spiking Neural Network ◽

Periodic Activity ◽

Information Dynamics ◽

Geometric Size ◽

Fully Connected ◽

Input Spike

Information about external world is delivered to the brain in the form of structured in time spike trains. During further processing in higher areas, information is subjected to a certain condensation process, which results in formation of abstract conceptual images of external world, apparently, represented as certain uniform spiking activity partially independent on the input spike trains details. Possible physical mechanism of condensation at the level of individual neuron was discussed recently. In a reverberating spiking neural network, due to this mechanism the dynamics should settle down to the same uniform/ periodic activity in response to a set of various inputs. Since the same periodic activity may correspond to different input spike trains, we interpret this as possible candidate for information condensation mechanism in a network. Our purpose is to test this possibility in a network model consisting of five fully connected neurons, particularly, the influence of geometric size of the network, on its ability to condense information. Dynamics of 20 spiking neural networks of different geometric sizes are modelled by means of computer simulation. Each network was propelled into reverberating dynamics by applying various initial input spike trains. We run the dynamics until it becomes periodic. The Shannon's formula is used to calculate the amount of information in any input spike train and in any periodic state found. As a result, we obtain explicit estimate of the degree of information condensation in the networks, and conclude that it depends strongly on the net's geometric size.

Download Full-text

Bayesian Optimization of Spiking Neural Network Parameters to Solving the Time Series Classification Task

Advances in Intelligent Systems and Computing - Biologically Inspired Cognitive Architectures (BICA) for Young Scientists ◽

10.1007/978-3-319-32554-5_6 ◽

2016 ◽

pp. 39-45 ◽

Cited By ~ 2

Author(s):

Alexey Chernyshev

Keyword(s):

Neural Network ◽

Time Series ◽

Bayesian Optimization ◽

Classification Task ◽

Spiking Neural Network ◽

Time Series Classification ◽

Network Parameters

Download Full-text

KLASIFIKASI CITRA GENUS PANTHERA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

Jurnal Ilmiah Informatika Komputer ◽

10.35760/ik.2019.v24i3.2364 ◽

2019 ◽

Vol 24 (3) ◽

pp. 220-228

Author(s):

Gusti Alfahmi Anwar ◽

Desti Riminarsih

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Model ◽

Neural Network Model ◽

Input Layer ◽

Fully Connected

Panthera merupakan genus dari keluarga kucing yang memiliki empat spesies popular yaitu, harimau, jaguar, macan tutul, singa. Singa memiliki warna keemasan dan tidak memilki motif, harimau memiliki motif loreng dengan garis-garis panjang, jaguar memiliki tubuh yang lebih besar dari pada macan tutul serta memiliki motif tutul yang lebih lebar, sedangkan macan tutul memiliki tubuh yang sedikit lebih ramping dari pada jaguar dan memiliki tutul yang tidak terlalu lebar. Pada penelitian ini dilakukan klasifikasi genus panther yaitu harimau, jaguar, macan tutul, dan singa menggunakan metode Convolutional Neural Network. Model Convolutional Neural Network yang digunakan memiliki 1 input layer, 5 convolution layer, dan 2 fully connected layer. Dataset yang digunakan berupa citra harimau, jaguar, macan tutul, dan singa. Data training terdiri dari 3840 citra, data validasi sebanyak 960 citra, dan data testing sebanyak 800 citra. Hasil akurasi dari pelatihan model untuk training yaitu 92,31% dan validasi yaitu 81,88%, pengujian model menggunakan dataset testing mendapatan hasil 68%. Hasil akurasi prediksi didapatkan dari nilai F1-Score pada pengujian didapatkan sebesar 78% untuk harimau, 70% untuk jaguar, 37% untuk macan tutul, 74% untuk singa. Macan tutul mendapatkan akurasi terendah dibandingkan 3 hewan lainnya tetapi lebih baik dibandingkan hasil penelitian sebelumnya.

Download Full-text