6 papers
A Latent Space Framework for Modeling Transient Engine Emissions Using Joint Embedding Predictive Architectures
Ganesh Sundaram, Tobias Gehra, Jonas Ulmen +3
Accurately modeling and controlling vehicle exhaust emissions during transient events, such as rapid acceleration, is critical for meeting environmental regulations and optimizing…
Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation
Ganesh Sundaram, Jonas Ulmen, Daniel Görges
The transition from monolithic to multi-component neural architectures in advanced neural network controllers poses substantial challenges due to the high computational complexity…
Application-Specific Component-Aware Structured Pruning of Deep Neural Networks in Control via Soft Coefficient Optimization
Ganesh Sundaram, Jonas Ulmen, Amjad Haider +1
Deep neural networks (DNNs) offer significant flexibility and robust performance. This makes them ideal for building not only system models but also advanced neural network control…
Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures
Jonas Ulmen, Ganesh Sundaram, Daniel Görges
With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for…
COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models
Ganesh Sundaram, Jonas Ulmen, Amjad Haider +1
The rapid growth of resource-constrained mobile platforms, including mobile robots, wearable systems, and Internet-of-Things devices, has increased the demand for computationally e…
Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis
Ganesh Sundaram, Jonas Ulmen, Daniel Görges
Deep neural networks (DNNs) deliver outstanding performance, but their complexity often prohibits deployment in resource-constrained settings. Comprehensive structured pruning fram…