Alpha-Net: Architecture, Models, and Applications
This work addresses efficiency and accuracy challenges in image recognition for researchers and practitioners, but it appears incremental as it builds on ResNet-like blocks and focuses on specific architectural tweaks.
The authors tackled the problem of computationally expensive and complex deep learning training by proposing Alpha-Net, a novel network architecture with ResNet-similar blocks, a custom loss function, and normalization, achieving up to 79.5% accuracy on a custom ImageNet-based dataset, with Alpha-Net v3 showing about 3% improvement over ResNet 50.
Deep learning network training is usually computationally expensive and intuitively complex. We present a novel network architecture for custom training and weight evaluations. We reformulate the layers as ResNet-similar blocks with certain inputs and outputs of their own, the blocks (called Alpha blocks) on their connection configuration form their own network, combined with our novel loss function and normalization function form the complete Alpha-Net architecture. We provided the empirical mathematical formulation of network loss function for more understanding of accuracy estimation and further optimizations. We implemented Alpha-Net with 4 different layer configurations to express the architecture behavior comprehensively. On a custom dataset based on ImageNet benchmark, we evaluate Alpha-Net v1, v2, v3, and v4 for image recognition to give the accuracy of 78.2%, 79.1%, 79.5%, and 78.3% respectively. The Alpha-Net v3 gives improved accuracy of approx. 3% over the last state-of-the-art network ResNet 50 on ImageNet benchmark. We also present an analysis of our dataset with 256, 512, and 1024 layers and different versions of the loss function. Input representation is also crucial for training as initial preprocessing will take only a handful of features to make training less complex than it needs to be. We also compared network behavior with different layer structures, different loss functions, and different normalization functions for better quantitative modeling of Alpha-Net.