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.

No abstract

The plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain’s self-modifying abilities play an essential role in learning and adaptation. The artificial neural networks with neuromodulated plasticity are used to implement transfer learning in the image classification domain. In particular, this has application in image detection, image segmentation, and transfer of learning parameters with significant results. This paper proposes a novel approach to enhance transfer learning accuracy in a heterogeneous source and target, using the neuromodulation of the Hebbian learning principle, called NDHTL (Neuromodulated Dopamine Hebbian Transfer Learning). Neuromodulation of plasticity offers a powerful new technique with applications in training neural networks implementing asymmetric backpropagation using Hebbian principles in transfer learning motivated CNNs (Convolutional neural networks). Biologically motivated concomitant learning, where connected brain cells activate positively, enhances the synaptic connection strength between the network neurons. Using the NDHTL algorithm, the percentage of change of the plasticity between the neurons of the CNN layer is directly managed by the dopamine signal’s value. The discriminative nature of transfer learning fits well with the technique. The learned model’s connection weights must adapt to unseen target datasets with the least cost and effort in transfer learning. Using distinctive learning principles such as dopamine Hebbian learning in transfer learning for asymmetric gradient weights update is a novel approach. The paper emphasizes the NDHTL algorithmic technique as synaptic plasticity controlled by dopamine signals in transfer learning to classify images using source-target datasets. The standard transfer learning using gradient backpropagation is a symmetric framework. Experimental results using CIFAR-10 and CIFAR-100 datasets show that the proposed NDHTL algorithm can enhance transfer learning efficiency compared to existing methods.

Microbial fuel cells (CS-UFC) utilize waste resources containing biodegradable materials that play an essential role in green energy. MFC technology generates “carbon-neutral” bioelectricity and involves a multidisciplinary approach to microbiology. MFCs will play an important role in the harvesting of “green electricity.” In this study, a single-chamber urea fuel cell is fabricated that uses these different wastewaters as fuel to generate power. Soil has been used to generate electrical power in microbial fuel cells and exhibited several potential applications to optimize the device; the urea fuel concentration is varied from 0.1 to 0.5 g/mL in a single-chamber compost soil urea fuel cell (CS-UFC). The proposed CS-UFC has a high power density and is suitable for cleaning chemical waste, such as urea, as it generates power by consuming urea-rich waste as fuel. The CS-UFC generates 12 times higher power than conventional fuel cells and exhibits size-dependent behavior. The power generation increases with a shift from the coin cell toward the bulk size. The power density of the CS-UFC is 55.26 mW/m2. This result confirmed that urea fuel significantly affects the power generation of single-chamber CS-UFC. This study aimed to reveal the effect of soil properties on the generated electric power from soil processes using waste, such as urea, urine, and industrial-rich wastewater as fuel. The proposed system is suitable for cleaning chemical waste; moreover, the proposed CS-UFC is a novel, sustainable, cheap, and eco-friendly design system for soil-based bulk-type design for large-scale urea fuel cell applications.