Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle

Abstract

Transfer learning algorithms have been widely studied for machine learning in recent times. In particular, in image recognition and classification tasks, transfer learning has shown significant benefits, and is getting plenty of attention in the research community. While performing a transfer of knowledge among source and target tasks, homogeneous dataset is not always available, and heterogeneous dataset can be chosen in certain circumstances. In this article, we propose a way of improving transfer learning efficiency, in case of a heterogeneous source and target, by using the Hebbian learning principle, called Hebbian transfer learning (HTL). In computer vision, biologically motivated approaches such as Hebbian learning represent associative learning, where simultaneous activation of brain cells positively affect the increase in synaptic connection strength between the individual cells. The discriminative nature of learning for the search of features in the task of image classification fits well to the techniques, such as the Hebbian learning rule—neurons that fire together wire together. The deep learning models, such as convolutional neural networks (CNN), are widely used for image classification. In transfer learning, for such models, the connection weights of the learned model should adapt to new target dataset with minimum effort. The discriminative learning rule, such as Hebbian learning, can improve performance of learning by quickly adapting to discriminate between different classes defined by target task. We apply the Hebbian principle as synaptic plasticity in transfer learning for classification of images using a heterogeneous source-target dataset, and compare results with the standard transfer learning case. Experimental results using CIFAR-10 (Canadian Institute for Advanced Research) and CIFAR-100 datasets with various combinations show that the proposed HTL algorithm can improve the performance of transfer learning, especially in the case of a heterogeneous source and target dataset.

Data protection based neural cryptography and deoxyribonucleic acid

“…The suggested system designated by adopts the Hebbian neural network infrastructure [5]- [9], but with several modifications has been done on HNN to the behalf of the proposed system. These modifications include: i) the number of input nodes and output nodes are equally; ii) the learning process is an unsupervised approach; iii) it is a single layer (no hidden layer), this topology provides an ability of simple implementation and fast learning speed compared to other networks with hidden layers; and iv) the propagation of the signals in the network will be in one direction only (feedforward), therefore each neuron will depend on the directed input signals only.…”

“…Therefore, it provides an algorithm for modifying the neuronal network relationship weight. The Hebb rule offers a simplified model based on physiology to simulate synaptic plasticity's activity-dependent characteristics and has been widely used in the artificial neural network field [5]- [9].…”

Machine Learning Approach for Modeling and Control of a Commercial Heliocentris FC50 PEM Fuel Cell System

“…The biological origin of Hebb's supervised learning was established from a neuroscience perspective: when two neurons are activated simultaneously, the link intensity (also called plasticity) is proportional to the multiplication of their stimulation [41,42]. Therefore, this concept can be translated mathematically for the adjustment of the PID parameters (k p , k i and k d ) which can be obtained through a neural settlement of Equation (8) as Equation (8) shows, where η i are learning rates that correspond to w i (k) [43].…”

Research on Airport Target Recognition under Low-Visibility Condition Based on Transfer Learning

“…Deep learning is one of the most popular machine learning algorithms in computer vision [27][28][29]. Its main motivation is to establish and simulate the neural network of the human brain for analytical learning.…”