Alam, Md. Golam RabiulHossain, Muhammad IqbalMohiuzzaman, Md.Abedin, Ahmad AbrarRahman, Shadab AfnanChowdhury, Shafaq ArefinAhmed, Shahadat2025-02-042025-02-04©20242024-10ID 20301361ID 20201080ID 21101076ID 21101064ID 20301481http://hdl.handle.net/10361/25284Cataloged from PDF version of thesis.Includes bibliographical references (pages 32-33).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.Federated Learning (FL) is a decentralized machine learning paradigm that enables training a global model across numerous edge devices while preserving data privacy. However, FL faces significant challenges, particularly in environments with heterogeneous hardware capabilities, communication burdens, and constrained resources. In this paper, we introduce a novel framework, TRI-FED-RKD, which incorporates forward and reverse knowledge distillation (RKD) along with FedAvg using a hybrid architecture of convolutional neural networks (CNNs) and spiking neural networks (SNNs). Our approach employs a tri-layer hierarchical aggregation-based architecture consisting of client devices, intermediate (middle) servers, and a global server. We compared two federated architectures: standard federated learning and federated learning with forward and reverse distillation in a hierarchical setting (TRI-FED-RKD). The same model is used across several datasets to evaluate the architectures, not the model performance. Depending on the use case, the network administrator can pick their own teacher and student models. The teacher model can also be different for each client if needed. This means that our architecture can deal with model heterogeneity when it comes to teacher models. We evaluate TRIFED- RKD on neuromorphic datasets such as DVS Gesture and NMNIST. We also tested it using non-neuromorphic datasets such as MNIST, EMNIST, and CIFAR10. Furthermore, we have shown that using forward and reverse knowledge distillation in federated learning can lead to much better performance than federated learning without knowledge distillation for non-neuromorphic datasets.42 pagesenBRAC University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Federated learningTri-layer architectureSNNSpiking neural networksDynamic vision sensorDVSCNNNeuromorphic datasetsConvolutional neural networkKnowledge distillationNeural networks (Computer science).Computer network architectures.Deep learning (Machine learning).Thesis