Deep Learning
Learning to Assimilate in Chaotic Dynamical Systems
Experimental results across several benchmark systems highlight the improved effectiveness of our approach over widely-used data assimilation methods.
EDGE: Explaining Deep Reinforcement Learning Policies
Gaussian process with a customized kernel function and an interpretable predictor.
EfficientFormer: Vision Transformers at MobileNet Speed Y anyu Li
Then we introduce a dimension-consistent pure transformer (without MobileNet blocks) as a design paradigm. Finally, we perform latency-driven slimming to get a series of final models dubbed EfficientFormer.
Structural Pruning via Latency-Saliency Knapsack
Structural pruning can simplify network architecture and improve inference speed.
Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks
How should the response profiles of these more "heterogeneous" cells be described, and how do they contribute to behavior? In this work, we took a computational approach to addressing these questions.
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training Pau de Jorge
RS-FGSM still leads to CO for larger perturbations, and proposed a computationally expensive regularizer (GradAlign) to avoid it.
Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems
Multi-agent control is a central theme in the Cyber-Physical Systems (CPS) . However, current control methods either receive non-Markovian states due to insufficient sensing and decentralized design, or suffer from poor convergence.
