Moaz Reyad developed a convolutional neural network model for hematologic disease analysis within the apache/singa repository, focusing on delivering a complete, extensible architecture for medical image classification. Using Python and leveraging deep learning and neural network techniques, he implemented convolutional, batch normalization, pooling, and fully connected layers, integrating a softmax cross-entropy loss function to support robust training. Moaz also created a factory function to instantiate the model and defined a set of supported optimizers, streamlining experimentation and standardizing training workflows. His work emphasized modularity and reusability, enabling rapid prototyping and laying groundwork for production evaluation in hematology image analysis.