Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning models by exploiting the relationships between continuously emerging class data. We find that applying human habits of organizing and connecting information can serve as an efficient strategy when training deep learning models. Specifically, by building a hierarchical tree structure based on the expanding set of labels, we gain fresh insights into the data, identifying groups of similar classes could easily cause confusion. Additionally, we delve deeper into the hidden connections between classes by exploring the original pretrained model's behavior through an optimal transport-based approach. From these insights, we propose a novel regularization loss function that encourages models to focus more on challenging knowledge areas, thereby enhancing overall performance. Experimentally, our method demonstrated significant superiority over the most robust state-of-the-art models on various benchmarks.

"Spirit" may one day be part of a pack of robots that become man's best friend on the Moon and Mars.

To control the walking gaits of a four-legged robot we present a novel neuromorphic VLSI chip that coordinates the relative phasing of the robot's legs similar to how spinal Central Pattern Generators are believed to control vertebrate locomotion [3]. The chip controls the leg move(cid:173) ments by driving motors with time varying voltages which are the out(cid:173) puts of a small network of coupled oscillators. The characteristics of the chip's output voltages depend on a set of input parameters. The rela(cid:173) tionship between input parameters and output voltages can be computed analytically for an idealized system. In practice, however, this ideal re(cid:173) lationship is only approximately true due to transistor mismatch and off(cid:173) sets.

A few years ago, we wrote about the tiniest little quadruped robot we'd ever seen--a mere 20 millimeters long, with a hip height of 5.6 mm and weight of about 1.6 gram. The designer, Ryan St. Pierre from Sarah Bergbreiter's lab at the University of Maryland, also showed us a picture of an even smaller version that weighed just 100 mg. "It's always a fun challenge to try to make robots as small as possible," he told us. "Currently, I am working on making a robot, of the same design, that would be 2.5 mm long, an order of magnitude smaller than the ones we presented at ICRA. Smaller robots can more easily go places that later robots can't, and having them in various sizes would increase their utility."