Surajit Majumder

Paritosh Ranjan, Surajit Majumder, Prodip Roy

Deep Learning, driven by neural networks, has led to groundbreaking advancements in Artificial Intelligence by enabling systems to learn and adapt like the human brain. These models have achieved remarkable results, particularly in data-intensive domains, supported by massive computational infrastructure. However, deploying such systems in Aerospace, where real time data processing and ultra low latency are critical, remains a challenge due to infrastructure limitations. This paper proposes a novel concept: the Airborne Neural Network a distributed architecture where multiple airborne devices each host a subset of neural network neurons. These devices compute collaboratively, guided by an airborne network controller and layer specific controllers, enabling real-time learning and inference during flight. This approach has the potential to revolutionize Aerospace applications, including airborne air traffic control, real-time weather and geographical predictions, and dynamic geospatial data processing. By enabling large-scale neural network operations in airborne environments, this work lays the foundation for the next generation of AI powered Aerospace systems.

Paritosh Ranjan, Surajit Majumder, Prodip Roy

The increasing scale of modern neural networks, exemplified by architectures from IBM (530 billion neurons) and Google (500 billion parameters), presents significant challenges in terms of computational cost and infrastructure requirements. As deep neural networks continue to grow, traditional training paradigms relying on monolithic GPU clusters become increasingly unsustainable. This paper proposes a distributed system architecture that partitions a neural network across multiple servers, each responsible for a subset of neurons. Neurons are classified as local or remote, with inter-server connections managed via a metadata-driven lookup mechanism. A Multi-Part Neural Network Execution Engine facilitates seamless execution and training across distributed partitions by dynamically resolving and invoking remote neurons using stored metadata. All servers share a unified model through a network file system (NFS), ensuring consistency during parallel updates. A Neuron Distributor module enables flexible partitioning strategies based on neuron count, percentage, identifiers, or network layers. This architecture enables cost-effective, scalable deployment of deep learning models on cloud infrastructure, reducing dependency on high-performance centralized compute resources.

Surajit Majumder, Paritosh Ranjan, Prodip Roy et al.

This paper introduces decentralized and modular neural network framework designed to enhance the scalability, interpretability, and performance of artificial intelligence (AI) systems. At the heart of this framework is a dynamic switch mechanism that governs the selective activation and training of individual neurons based on input characteristics, allowing neurons to specialize in distinct segments of the data domain. This approach enables neurons to learn from disjoint subsets of data, mimicking biological brain function by promoting task specialization and improving the interpretability of neural network behavior. Furthermore, the paper explores the application of federated learning and decentralized training for real-world AI deployments, particularly in edge computing and distributed environments. By simulating localized training on non-overlapping data subsets, we demonstrate how modular networks can be efficiently trained and evaluated. The proposed framework also addresses scalability, enabling AI systems to handle large datasets and distributed processing while preserving model transparency and interpretability. Finally, we discuss the potential of this approach in advancing the design of scalable, privacy-preserving, and efficient AI systems for diverse applications.