No abstract

Activation functions facilitate deep neural networks by introducing non-linearity to the learning process. The non-linearity feature gives the neural network the ability to learn complex patterns. Recently, the most widely used activation function is the Rectified Linear Unit (ReLU). Though, other various existing activation including hand-designed alternatives to ReLU have been proposed. However, none has succeeded in replacing ReLU due to their existing inconsistencies. In this work, activation function called ReLU-Memristor-like Activation Function (RMAF) is proposed to leverage benefits of negative values in neural networks. RMAF introduces a constant parameter (α) and a threshold parameter (p) making the function smooth, non-monotonous, and introduces non-linearity in the network. Our experiments show that, the RMAF works better than ReLU and other activation functions on deeper models and across number of challenging datasets. Firstly, experiments are performed by training and classifying on multi-layer perceptron (MLP) over benchmark data such as the Wisconsin breast cancer, MNIST, Iris and Car evaluation. RMAF achieves high performance of 98.74%, 99.67%, 98.81% and 99.42% respectively, compared to Sigmoid, Tanh and ReLU. Secondly, experiments were performed on convolution neural network (ResNet) over MNIST, CIFAR-10 and CIFAR-100 data and observed the proposed activation function achieves higher performance accuracy of 99.73%, 98.77% and 79.82% respectively than Tanh, ReLU and Swish. Additionally, we experimented our work on deep networks i.e. squeeze network (SqueezeNet), Dense connected neural network (DenseNet121) and ImageNet dataset, which RMAF produced the best performance. We note that, the RMAF converges faster than the other functions and can replace ReLU in any neural network due to the efficiency, scalability and its similarity to both ReLU and Swish.

No abstract

No abstract

Crop diseases contribute significantly to food insecurity, malnutrition, and poverty in Africa where the majority of the population is into Agriculture. Manual plant disease recognition methods are widespread but limited, ineffective, costly, and time-consuming making the need to search for automatic and efficient methods of recognition more crucial. Machine learning and Convolutional Neural Networks have been applied in other jurisdictions in an attempt to solve these problems. They have achieved impressive results in this domain but tend to be 'data-hungry', invariant, and vulnerable to attacks that can easily lead to misclassifications. Capsule Networks, on the other hand, avoids the weaknesses of CNNs and has not been widely used in this area. This article, therefore, proposes the use of Gabor and Capsule network to recognize blurred, deformed, and unseen tomato and citrus disease images. Experimental results show that the proposed model can achieve a 98.13% test accuracy which is comparable to the performance of state-of-theart CNN models in the literature. Also, the proposed model outperformed two state-of-the-art deep learning models (which were implemented as baseline models) in terms of robustness, flexibility, fast converges, and having fewer parameters. This work can be extended to other crops and may well serve as a useful tool for the recognition of unseen plant diseases under bad weather and bad illumination conditions.

No abstract

Capsule Networks (CapsNets) excel on simple image recognition problems. However, they fail to perform on complex images with high similarity and background objects. This paper proposes Local Binary Pattern (LBP) k-means routing and evaluates its performance on three publicly available plant disease datasets containing images with high similarity and background objects. The proposed routing algorithm adopts the squared Euclidean distance, sigmoid function, and a ‘simple-squash’ in place of dot product, SoftMax normalizer, and the squashing function found respectively in the dynamic routing algorithm. Extensive experiments conducted on the three datasets showed that the proposed model achieves consistent improvement in test accuracy across the three datasets as well as allowing an increase in the number of routing iterations with no performance degradation. The proposed model outperformed a baseline CapsNet by 8.37% on the tomato dataset with an overall test accuracy of 98.80%, comparable to state-of-the-art models on the same datasets.

No abstract