Developing a Machine-Learning Algorithm to Diagnose Age-Related Macular Degeneration

Today, more than 12 million people over the age of 40 suffer from ocular diseases. Most commonly, older patients are susceptible to age related macular degeneration, an eye disease that causes blurring of the central vision due to the deterioration of the retina. The former can only be detected through complex and expensive imaging software, markedly a visual field test; this leaves a significant population with untreated eye disease and holds them at risk for complete vision loss. The use of machine learning algorithms has been proposed for treating eye disease. However, the development of these models is limited by a lack of understanding regarding appropriate model and training parameters to maximize model performance. In our study, we address these points by generating 6 models, each with a learning rate of 1 * 10^n where n is 0, -1, -2, ... -6, and calculated a f1 score for each of the models. Our analysis shows that sample imbalance is a key challenge in training of machine learning models and can result in deceptive improvements in training cost which does not translate to true improvements in model predictive performance. Considering the wide ranging impact of the disease and its adverse effects, we developed a machine learning algorithm to treat the same. We trained our model on varying eye disease datasets consisting of over 5000 patients, and the pictures of their infected eyes. In the future, we hope this model is used extensively, especially in areas that are under-resourced, to better diagnose eye disease and improve well being for humanity.

FPGA Implementation of Simplified Spiking Neural Network

Spiking Neural Networks (SNN) are third-generation Artificial Neural Networks (ANN) which are close to the biological neural system. In recent years SNN has become popular in the area of robotics and embedded applications, therefore, it has become imperative to explore its real-time and energy-efficient implementations. SNNs are more powerful than their predecessors because they encode temporal information and use biologically plausible plasticity rules. In this paper, a simpler and computationally efficient SNN model using FPGA architecture is described. The proposed model is validated on a Xilinx Virtex 6 FPGA and analyzes a fully connected network which consists of 800 neurons and 12,544 synapses in real-time.