Related papers: The Peano software - parallel, automaton-based, dy…
The ability of a robot to plan complex behaviors with real-time computation, rather than adhering to predesigned or offline-learned routines, alleviates the need for specialized algorithms or training for each problem instance. Monte Carlo…
Multinomial Logistic Regression is a well-studied tool for classification and has been widely used in fields like image processing, computer vision and, bioinformatics, to name a few. Under a supervised classification scenario, a…
Design exploration is an important step in the engineering design process. This involves the search for design/s that meet the specified design criteria and accomplishes the predefined objective/s. In recent years, machine learning-based…
We present here the result of continuation work, performed to further fulfill the vision we outlined in [Harel,Lekien,P\'eba\"y-2017] for the visualization and analysis of tree-based adaptive mesh refinement (AMR) simulations, using the…
The ability to harness heterogeneous, dynamically available "Grid" resources is attractive to typically resource-starved computational scientists and engineers, as in principle it can increase, by significant factors, the number of cycles…
We present a GPU-based system for automatic differentiation (AD) of functions defined on triangle meshes, designed to exploit the locality and sparsity in mesh-based computation. Our system evaluates derivatives using per-element…
On-device fine-tuning is a critical capability for edge AI systems, which must support adaptation to different agentic tasks under stringent memory constraints. Conventional backpropagation (BP)-based training requires storing layer…
The issue of data-driven neural network model construction is one of the core problems in the domain of Artificial Intelligence. A standard approach assumes a fixed architecture with trainable weights. A conceptually more advanced…
Remote memory techniques for datacenter applications have recently gained a great deal of popularity. Existing remote memory techniques focus on the efficiency of a single application setting only. However, when multiple applications co-run…
Evolving smart grids require flexible and adaptive control methods. A harmonized hybrid cyber-physical framework, which considers both physical and cyber layers and ensures adaptability, is one of the critical challenges to enable…
Machine learning algorithms have made significant advances in many applications. However, their hardware implementation on the state-of-the-art platforms still faces several challenges and are limited by various factors, such as memory…
Distributed AI systems face critical memory management challenges across computation, communication, and deployment layers. RRAM based in memory computing suffers from scalability limitations due to device non idealities and fixed array…
Many modern programming languages are shifting toward a functional style for collection interfaces such as sets, maps, and sequences. Functional interfaces offer many advantages, including being safe for parallelism and providing simple and…
A key step during industrial design is the passing of design information from computer aided design (CAD) to analysis tools (CAE) and vice versa. Here, one is faced with a severe incompatibility in geometry representation: While CAD is…
Differentiable programming is the combination of classical neural networks modules with algorithmic ones in an end-to-end differentiable model. These new models, that use automatic differentiation to calculate gradients, have new learning…
Neural networks (NNs) are growing in importance and complexity. A neural network's performance (and energy efficiency) can be bound either by computation or memory resources. The processing-in-memory (PIM) paradigm, where computation is…
Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs). To alleviate their excessive computational demands, developers have traditionally resorted to cloud offloading,…
The ever-increasing computation complexity of fast-growing Deep Neural Networks (DNNs) has requested new computing paradigms to overcome the memory wall in conventional Von Neumann computing architectures. The emerging Computing-In-Memory…
As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge when adapting to new tasks, resulting in severe performance…
Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we…