Related papers: AIRCHITECT: Learning Custom Architecture Design an…
Machine learning pipelines that include a combinatorial optimization layer can give surprisingly efficient heuristics for difficult combinatorial optimization problems. Three questions remain open: which architecture should be used, how…
Techniques for automatically designing deep neural network architectures such as reinforcement learning based approaches have recently shown promising results. However, their success is based on vast computational resources (e.g. hundreds…
Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. In this paper, we consider automating the search space design to minimize human interference,…
Modern applications process massive data volumes that overwhelm the storage and retrieval capabilities of memory systems, making memory the primary performance and energy-efficiency bottleneck of computing systems. Although many…
ReRAM-based in-memory computing (IMC) architectures are promising candidates for energy-efficient matrix-vector multiplication. While scaling the size of ReRAM arrays allows for the amortization of power-hungry peripheral circuits like DACs…
Path planning is a classic problem for autonomous robots. To ensure safe and efficient point-to-point navigation an appropriate algorithm should be chosen keeping the robot's dimensions and its classification in mind. Autonomous robots use…
Topology Optimization (TO) provides a systematic approach for obtaining structure design with optimum performance of interest. However, the process requires numerical evaluation of objective function and constraints at each iteration, which…
The structural design process for buildings is time-consuming and laborious. To automate this process, structural engineers combine optimization methods with simulation tools to find an optimal design with minimal building mass subject to…
Determination of design parameters based on electromagnetic simulations of microwave circuits is an iterative and often time-consuming procedure. Space mapping is a powerful technique to optimize such complex models by efficiently…
The automation of feature extraction of machine learning has been successfully realized by the explosive development of deep learning. However, the structures and hyperparameters of deep neural network architectures also make huge…
Buildings sector is one of the major consumers of energy in the United States. The buildings HVAC (Heating, Ventilation, and Air Conditioning) systems, whose functionality is to maintain thermal comfort and indoor air quality (IAQ), account…
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model…
Topology optimization is widely used by engineers during the initial product development process to get a first possible geometry design. The state-of-the-art is the iterative calculation, which requires both time and computational power.…
Context. Despite the increasing adoption of Machine Learning Operations (MLOps), teams still encounter challenges in effectively applying this paradigm to their specific projects. While there is a large variety of available tools usable for…
Accurate mathematical models of aerodynamic properties play an important role in the aerospace field. In some cases, system parameters of an aircraft can be estimated reliably only via flight tests. In order to obtain meaningful…
Designing mechanically efficient geometry for architectural structures like shells, towers, and bridges, is an expensive iterative process. Existing techniques for solving such inverse problems rely on traditional optimization methods,…
When planning motions in a configuration space that has underlying symmetries (e.g. when manipulating one or multiple symmetric objects), the ideal planning algorithm should take advantage of those symmetries to produce shorter…
The influence of deep learning is continuously expanding across different domains, and its new applications are ubiquitous. The question of neural network design thus increases in importance, as traditional empirical approaches are reaching…
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this…
Application autotuning is a promising path investigated in literature to improve computation efficiency. In this context, the end-users define high-level requirements and an autonomic manager is able to identify and seize optimization…