… Federated learning aims to address the security and networking concerns by keeping the
datasets local at devices, whereas STOIC intelligently offloads jobs across multiple tiers of …

… an accelerated RL method that can learn proper VNF sizing and placement on a real network
under … We evaluated environment adaptability of the proposed method on three scenarios (…

… accelerator design. This paper systematically investigates the interconnection networks in
modern DNN accelerator … The adaptability of the proposed NoC comes from the adoption of an …

… for complex data dependency learning via mutually adaptable feature selection and model
update. … Note that other models, such as the graph neural networks, can also be used as BUs …

… Networks (RNNs) for tasks such as Automatic Speech Recognition has fostered interest in
RNN inference acceleration. … To do so, we propose Sharp as a hardware accelerator, which …

… of a deep neural network after model training, we propose an accelerated edge cloud …
deep learning scheme. The incremental learning scheme can perform realtime learning by …

… Sharp, an adaptable and energy-efficient architecture for RNN inference acceleration. We
show that … Furthermore, we introduce dynamic reconfigurability that allows the accelerator to …

… network algorithms [8], and heterogeneous systems built with GPUs and APUs for deep learning
accelerations [9]… the circuit realization of neural network models. The specialty of memris…

… for accelerating deep neural networks. An FPGA ‘resource-adaptable’ neural network accelerator
is … The architecture and behavior of this accelerator is determined only by the way its C …

… designed to increase digital skill adaptability. This Learning Skills Bridge learning accelerator
training package (LSB) … Thus, for Network-Centric Warfare to be a success, adaptability in …