Search

While contrastive approaches of self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point (positive pairs) and maximizing views from different data points (negative pairs), recent non-contrastive SSL (e.g., BYOL and SimSiam)...

High-dimensional partial differential equations (PDEs) are ubiquitous in economics, science and engineering. However, their numerical treatment poses formidable challenges since traditional grid-based methods tend to be frustrated by the curse of dimensionality. In this paper, we argue that tensor...

The physicist, neuroscientist, and PhD candidate creates augmentative technology for children with neurodevelopmental differences.

Among the four big NoSQL database types, key-value stores are probably the most popular ones due to their simplicity and fast performance. Let’s further explore how key-value stores work and what are their practical uses.

While global warming has generally increased the occurrence of extreme precipitation, the physical mechanisms by which climate change alters regional and local precipitation extremes remain uncertain, with debate about the role of changes in the atmospheric circulation. We use a convolutional neural...

The circadian clock is an important adaptation to life on Earth. Here, we use machine learning to predict complex, temporal, and circadian gene expression patterns in Arabidopsis. Most significantly, we classify circadian genes using DNA sequence features generated de novo from public, genomic...

Visual cognition of primates is superior to that of artificial neural networks in its ability to 'envision' a visual object, even a newly-introduced one, in different attributes including pose, position, color, texture, etc. To aid neural networks to envision objects with different attributes, we...

Accurate prediction of driving risk is challenging due to the rarity of crashes and individual driver heterogeneity. One promising direction of tackling this challenge is to take advantage of telematics data, increasingly available from connected vehicle technology, to obtain dense risk predictors...

Disinformation through fake news is an ongoing problem in our society and has become easily spread through social media. The most cost and time effective way to filter these large amounts of data is to use a combination of human and technical interventions to identify it. From a technical...

We demonstrate that the consideration of material uncertainty can dramatically impact the optimal topological micro-structural configuration of mechanical metamaterials. The robust optimization problem is formulated in such a way that it facilitates the emergence of extreme mechanical properties of...

The full value of your deep learning models comes from enabling others to use them. Learn how to deploy your model to the web and access it as a REST API, and begin to share the power of your machine learning development with the world.

Developing machine learning models that can perform predictive functions on data it has never seen before has become an important research area called zero-shot learning. We tend to be pretty great at recognizing things in the world we never saw before, and zero-shot learning offers a possible path...

SensiCut, a smart material-sensing platform for laser cutters, can differentiate between 30 materials commonly found in makerspaces and workshops.

Digital inline holography is an amazingly simple and effective approach for 3D imaging, to which particle tracking velocimetry is of particular interest. Conventional digital holographic particle tracking velocimetry techniques are computationally separated in particle and flow reconstruction, plus...

We show that unsupervised machine learning (ML) using principal-component (PC) analysis provides a straightforward pathway for developing accurate and interpretable electronic-structure descriptors of the chemical and catalytic properties of materials. We demonstrate the approach by finding...

Inferring the properties of a scattering objective by analyzing the optical far-field responses within the framework of inverse problems is of great practical significance. However, it still faces major challenges when the parameter range is growing and involves inevitable experimental noises. Here...

In the mid-Holocene (5000 - 3000 cal B.P.), Native American groups constructed shell rings, a type of circular midden, in coastal areas of the American Southeast. These deposits provide important insights into Native American socioeconomic organization but are also quite rare: only about 50 such...

Single-particle tracking (SPT) is a key tool for quantitative analysis of dynamic biological processes and has provided unprecedented insights into a wide range of systems such as receptor localization, enzyme propulsion, bacteria motility, and drug nanocarrier delivery. The inherently complex...

Precise measuring of urban façade color is necessary for urban color planning. The existing manual methods of measuring building façade color are limited by time and labor costs and hardly carried out on a city scale. These methods also make it challenging to identify the role of the building...

Pathology is practiced by visual inspection of histochemically stained tissue slides. While the hematoxylin and eosin (H&E) stain is most commonly used, special stains can provide additional contrast to different tissue components. Here, we demonstrate the utility of supervised learning-based...