— Recursive Neural Networks (RNNs) and Graph Neural Networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing fram...
Vincenzo Di Massa, Gabriele Monfardini, Lorenzo Sa...
The DAG-based task graph model has been found effective in scheduling for performance prediction and optimization of parallel applications. However the scheduling complexity and s...
We present a fine-grain dynamic instruction placement algorithm for small L0 scratch-pad memories (spms), whose unit of transfer can be an individual instruction. Our algorithm ca...
— This paper presents a dynamic and distributed reconfiguration planning algorithm for chain-type selfreconfigurable robots, by which a robot can autonomously self-reconfigure fr...
We study the performance of packet routing on arrays (or meshes) with bounded buffers in the routing switches, assuming that new packets are continuously inserted at all the nodes....