STOCHASTIC PSEUDOSPIN NEURAL NETWORK WITH TRIDIAGONAL SYNAPTIC CONNECTIONS

Context. To reduce the computational resource time in the problems of diagnosing and recognizing distorted images based on a fully connected stochastic pseudospin neural network, it becomes necessary to thin out synaptic connections between neurons, which is solved using the method of diagonalizing the matrix of synaptic connections without losing interaction between all neurons in the network. Objective. To create an architecture of a stochastic pseudo-spin neural network with diagonal synaptic connections without loosing the interaction between all the neurons in the layer to reduce its learning time. Method. The paper uses the Hausholder method, the method of compressing input images based on the diagonalization of the matrix of synaptic connections and the computer mathematics system MATLAB for converting a fully connected neural network into a tridiagonal form with hidden synaptic connections between all neurons. Results. We developed a model of a stochastic neural network architecture with sparse renormalized synaptic connections that take into account deleted synaptic connections. Based on the transformation of the synaptic connection matrix of a fully connected neural network into a Hessenberg matrix with tridiagonal synaptic connections, we proposed a renormalized local Hebb rule. Using the computer mathematics system “WolframMathematica 11.3”, we calculated, as a function of the number of neurons N, the relative tuning time of synaptic connections (per iteration) in a stochastic pseudospin neural network with a tridiagonal connection Matrix, relative to the tuning time of synaptic connections (per iteration) in a fully connected synaptic neural network. Conclusions. We found that with an increase in the number of neurons, the tuning time of synaptic connections (per iteration) in a stochastic pseudospin neural network with a tridiagonal connection Matrix, relative to the tuning time of synaptic connections (per iteration) in a fully connected synaptic neural network, decreases according to a hyperbolic law. Depending on the direction of pseudospin neurons, we proposed a classification of a renormalized neural network with a ferromagnetic structure, an antiferromagnetic structure, and a dipole glass.

Implementasi Algoritma Hebb Rule Pada Diagnosa Penyakit Kolik Abdomen Pada Orang Dewasa

In the current era of globalization, the development of computers in the health sector has become increasingly rapid. Computerized systems are needed especially in handling a disease. Because sometimes doctors, nurses find it difficult to know the type of illness suffered by adults, children and the elderly without a good computerized system. Abdominal colic, for example. Abdominal colic is a disease where there is an unpleasant feeling in the oral cavity between the thigh border and the chest rib border. This disease is caused by several factors, for example, eating is already full, eating a lot of acid, spicy and also drinking lots of alcohol. And usually occurs in adults. Where symptoms are symptoms such as nausea, vomiting and noisy intestines and excessive farts. With these symptoms, which becomes a control that a person has abdominal colic disease. Therefore the author made a study of the implementation of the HB rule on the diagnosis of abdominal colic disease. Theebb rule algorithm is a simple and uncomplicated learning method in the process, with the aim of minimizing the risk of disease problems that occur in patients, especially adults

Modeling Hebb Learning Rule for Unsupervised Learning

This paper presents to model the Hebb learning rule and proposes a neuron learning machine (NLM). Hebb learning rule describes the plasticity of the connection between presynaptic and postsynaptic neurons and it is unsupervised itself. It formulates the updating gradient of the connecting weight in artificial neural networks. In this paper, we construct an objective function via modeling the Hebb rule. We make a hypothesis to simplify the model and introduce a correlation based constraint according to the hypothesis and stability of solutions. By analysis from the perspectives of maintaining abstract information and increasing the energy based probability of observed data, we find that this biologically inspired model has the capability of learning useful features. NLM can also be stacked to learn hierarchical features and reformulated into convolutional version to extract features from 2-dimensional data. Experiments on single-layer and deep networks demonstrate the effectiveness of NLM in unsupervised feature learning.

DETEKSI GANGGUAN LAMBUNG MELALUI CITRA IRIS MATA MENGGUNAKAN METODE JARINGAN SYARAF TIRUAN HEBB RULE

Iridology merupakan metode menganalisis iris mata untuk mendeteksi kelemahan organ tubuh melalui ciri-ciri maupun tanda-tanda yang muncul pada iris mata. Iris mata memiliki kelebihan spesifik yang dapat merekam semua kondisi organ tubuh, salah satunya adalah organ lambung. Dengan memanfaatkan biometrik dan ilmu iridologi, maka pada Tugas Akhir ini dibangun sebuah perangkat lunak untuk mendeteksi gangguan lambung dengan menggunakan metode hebb rule. Mekanisme yang dilakukan oleh sistem dimulai dengan menginput citra iris mata yang kemudian diubah menjadi citra grayscale. Citra iris grayscale ditransformasikan ke dalam koordinat polar untuk memudahkan proses pengambilan daerah lambung pada lapisan pertama iris. Citra iris daerah lambung selanjutnya dilakukan proses pendeteksian tepi dengan menggunakan operator canny yang akan digunakan sebagai input metode hebb rule. Metode hebb rule yang akan menentukan iris mata yang terdapat gangguan lambung ataupun tidak dengan menghitung bobot dan net dari setiap nilai vektor yang membentuk pada pola iris daerah lambung. Terdapat beberapa faktor yang dapat mempengaruhi proses pendeteksian, seperti noise pada citra masukan dan pencahayaan yang masuk ke iris daerah lambung. Dari 40 citra iris mata yang diuji terdapat 31 citra yang mampu dikenali. Sehingga tingkat akurasi sistem ini adalah 77,50%. Berdasarkan hasil tersebut, maka dapat disimpulkan bahwa sistem ini mampu mendeteksi gangguan lambung melalui citra iris mata.Kata Kunci : Iridology, iris mata, lambung, citra polar, canny, hebb rule.

A Biologically Inspired Computational Model of Basal Ganglia in Action Selection

The basal ganglia (BG) are a subcortical structure implicated in action selection. The aim of this work is to present a new cognitive neuroscience model of the BG, which aspires to represent a parsimonious balance between simplicity and completeness. The model includes the 3 main pathways operating in the BG circuitry, that is, the direct (Go), indirect (NoGo), and hyperdirect pathways. The main original aspects, compared with previous models, are the use of a two-term Hebb rule to train synapses in the striatum, based exclusively on neuronal activity changes caused by dopamine peaks or dips, and the role of the cholinergic interneurons (affected by dopamine themselves) during learning. Some examples are displayed, concerning a few paradigmatic cases: action selection in basal conditions, action selection in the presence of a strong conflict (where the role of the hyperdirect pathway emerges), synapse changes induced by phasic dopamine, and learning new actions based on a previous history of rewards and punishments. Finally, some simulations show model working in conditions of altered dopamine levels, to illustrate pathological cases (dopamine depletion in parkinsonian subjects or dopamine hypermedication). Due to its parsimonious approach, the model may represent a straightforward tool to analyze BG functionality in behavioral experiments.

Applying Different Learning Rules in Neuro-Symbolic Integration

Pseudo inverse learning rule and new activation unction performance will be evaluated and compared with the primitive learning rule, Hebb rule. Comparisons are made between these three rules to see which rule is better or outperformed other rules in the aspects of computation time, memory and complexity. From the computer simulation that has been carried out, the new activation function performs better than the other two learning methods.