Neural network relief: a pruning algorithm based on neural activity

Current deep neural networks (DNNs) are overparameterized and use most of their neuronal connections during inference for each task. The human brain, however, developed specialized regions for different tasks and performs inference with a small fraction of its neuronal connections. We propose an iterative pruning strategy introducing a simple...

Continual learning for surface defect segmentation by subnetwork creation and selection

We introduce a new continual (or lifelong) learning algorithm called LDA-CP &S that performs segmentation tasks without undergoing catastrophic forgetting. The method is applied to two different surface defect segmentation problems that are learned incrementally, i.e., providing data about one type of defect at a time, while still being...

Ultralight Membrane Structures Toward a Sustainable Environment

The building construction industry is the largest anthropogenic source of pollution, with massive energy consumption and substantial CO2 emissions. Lightweight tension structures allow the simultaneous implementation of several sustainable strategies by using recyclable low-carbon structural membranes offering a greener alternative to glass and...

Centimeter-scale nanomechanical resonators with low dissipation

High-aspect-ratio mechanical resonators are pivotal in precision sensing, from macroscopic gravitational wave detectors to nanoscale acoustics. However, fabrication challenges and high computational costs have limited the length-to-thickness ratio of these devices, leaving a largely unexplored regime in nano-engineering. We present...

Cooperative data-driven modeling

Data-driven modeling in mechanics is evolving rapidly based on recent machine learning advances, especially on artificial neural networks. As the field matures, new data and models created by different groups become available, opening possibilities for cooperative modeling. However, artificial neural networks suffer from catastrophic...

Continual prune-and-select: Class-incremental learning with specialized subnetworks

The human brain is capable of learning tasks sequentially mostly without forgetting. However, deep neural networks (DNNs) suffer from catastrophic forgetting when learning one task after another. We address this challenge considering a class-incremental learning scenario where the DNN sees test data without knowing the task from which this...

High-Strength Amorphous Silicon Carbide for Nanomechanics

For decades, mechanical resonators with high sensitivity have been realized using thin-film materials under high tensile loads. Although there are remarkable strides in achieving low-dissipation mechanical sensors by utilizing high tensile stress, the performance of even the best strategy is limited by the tensile fracture strength of the...

Generation of design allowables on the open hole tensile strength of composite laminates using sensitivity analysis and uncertainty quantification framework

Aeronautical industries are concerned about the cost effective generation of design allowables for composite laminates. Design allowables take into account the variabilities arising from different sources (material, manufacturing, defects etc.,) which are determined using expensive and time consuming experimental campaigns....

Quantifying nanoscale forces using machine learning in dynamic atomic force microscopy

Dynamic atomic force microscopy (AFM) is a key platform that enables topological and nanomechanical characterization of novel materials. This is achieved by linking the nanoscale forces that exist between the AFM tip and the sample to specific mathematical functions through modeling. However, the main challenge in dynamic AFM is to quantify...

Adaptivity for clustering-based reduced-order modeling of localized history-dependent phenomena

This article introduces adaptivity in Clustering-based Reduced Order Models (ACROMs). The strategy is demonstrated for a particular CROM called Self-Consistent Clustering Analysis (SCA), extending it into the Adaptive Self-Consistent Clustering Analysis (ASCA) method. This is shown to improve predictions of Representative Volume Elements ...

Spiderweb Nanomechanical Resonators via Bayesian Optimization: Inspired by Nature and Guided by Machine Learning

From ultrasensitive detectors of fundamental forces to quantum networks and sensors, mechanical resonators are enabling next-generation technologies to operate in room-temperature environments. Currently, silicon nitride nanoresonators stand as a leading microchip platform in these advances by allowing for mechanical resonators whose motion...

Sparse quantum Gaussian processes to counter the curse of dimensionality

Gaussian processes are well-established Bayesian machine learning algorithms with significant merits, despite a strong limitation: lack of scalability. Clever solutions address this issue by inducing sparsity through low-rank approximations, often based on the Nystrom method. Here, we propose a different method to achieve better scalability...

A methodology to generate design allowables of composite laminates using machine learning

This work represents the first step towards the application of machine learning techniques in the prediction of statistical design allowables of composite laminates. Building on data generated analytically, four machine algorithms (XGBoost, Random Forests, Gaussian Processes and Artificial Neural Networks) are used to predict the notched...

Compliant Mechanisms That Use Static Balancing to Achieve Dramatically Different States of Stiffness

Stiffness in compliant mechanisms can be dramatically altered and even eliminated entirely by using static balancing. This requires elastic energy to be inserted before operation, which is most often done with an additional device or preloading assembly. Adding such devices contrasts starkly with primary motivations for using compliant...

Monolithic binary stiffness building blocks for mechanical digital machines

We introduce two essential building blocks with binary stiffness for mechanical digital machines. The large scale fully compliant mechanisms have rectilinear and rotational kinematics and use a new V-shaped negative stiffness structure to create two extreme states of stiffness by static balancing. The use of a mechanical bistable switch...

A numerical Bayesian-calibrated characterization method for multiscale prepreg preforming simulations with tension-shear coupling

Carbon fiber reinforced plastics (CFRPs) are attracting growing attention in industry because of their enhanced properties. Preforming of thermoset carbon fiber prepregs is one of the most common production techniques of CFRPs. To simulate preforming, several computational methods have been developed. Most of these methods, however, obtain...

Bayesian Machine Learning in metamaterial design: Fragile becomes supercompressible

Designing future-proof materials goes beyond a quest for the best. The next generation of materials needs to be adaptive, multipurpose, and tunable. This is not possible by following the traditional experimentally guided trial-and-error process, as this limits the search for untapped regions of the solution space. Here, a computational data...

Deep learning predicts path-dependent plasticity

Plasticity theory aims at describing the yield loci and work hardening of a material under general deformation states. Most of its complexity arises from the nontrivial dependence of the yield loci on the complete strain history of a material and its microstructure. This motivated 3 ingenious simplifications that underpinned a century of...