Search

So much time and effort can go into training your machine learning models. But, shut down the notebook or system, and all those trained weights and more vanish with the memory flush. Saving your models to maximize reusability is key for efficient productivity.

Differentiable Neural Architecture Search is one of the most popular Neural Architecture Search (NAS) methods for its search efficiency and simplicity, accomplished by jointly optimizing the model weight and architecture parameters in a weight-sharing supernet via gradient-based algorithms. At the...

We analyze the convergence of the averaged stochastic gradient descent for overparameterized two-layer neural networks for regression problems. It was recently found that a neural tangent kernel (NTK) plays an important role in showing the global convergence of gradient-based methods under the NTK...

We present a neural rendering approach for binaural sound synthesis that can produce realistic and spatially accurate binaural sound in realtime. The network takes, as input, a single-channel audio source and synthesizes, as output, two-channel binaural sound, conditioned on the relative position...

Creating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms...

The ever-changing nature of human environments presents great challenges to robot manipulation. Objects that robots must manipulate vary in shape, weight, and configuration. Important properties of the robot, such as surface friction and motor torque constants, also vary over time. Before robot...

Over history, games have served multiple purposes. It serves as a fun activity for players who need the entertainment to become test-beds for artificial intelligence. Solving games is beneficial in providing a better understanding of how information is progressing throughout the game. Uncertainty in...

In order to improve Remaining Useful Life (RUL) prediction accuracy for rolling bearings under defect progressing, the robustness for individual differences and the fluctuation of vibration features are challenging issues. In this research, we propose a novel RUL prediction framework based on a...

Cell-level quantitative features of retinal ganglion cells (GCs) are potentially important biomarkers for improved diagnosis and treatment monitoring of neurodegenerative diseases such as glaucoma, Parkinson’s disease, and Alzheimer’s disease. Yet, due to limited resolution, individual GCs cannot be...

In this article, we explore how to build a pipeline and process real-time video with Deep Learning to apply this approach to business use cases overviewed in our research.

Machine learning software advances could help anesthesiologists optimize drug dose.

The technology uses tactile sensing to identify objects underground, and might one day help disarm land mines or inspect cables.

Many resources exist for the self-study of data science. In our modern age of information technology, an enormous amount of free learning resources are available to anyone, and with effort and dedication, you can master the fundamentals of data science.

The inverse renormalization group is studied based on the image super-resolution using the deep convolutional neural networks. We consider the improved correlation configuration instead of spin configuration for the spin models, such as the two-dimensional Ising and three-state Potts models. We...

Fire fighter fatalities and injuries in the U.S. remain too high and fire fighting too hazardous. Until now, fire fighters rely only on their experience to avoid life-threatening fire events, such as flashover. In this paper, we describe the development of a flashover prediction model which can be...

Synthetic data can be used to test new products and services, validate models, or test performances because it mimics the statistical property of production data. Today you'll find different types of structured and unstructured synthetic data.

In a first, the digital fiber contains memory, temperature sensors, and a trained neural network program for inferring physical activity.

Angkor is one of the world’s largest premodern settlement complexes (9th to 15th centuries CE), but to date, no comprehensive demographic study has been completed, and key aspects of its population and demographic history remain unknown. Here, we combine lidar, archaeological excavation data...

The Fields Medal, often referred as the Nobel Prize of mathematics, is awarded to no more than four mathematicians under the age of 40, every 4 years. In recent years, its conferral has come under scrutiny of math historians, for rewarding the existing elite rather than its original goal of...

Deep learning implementations on CPUs (Central Processing Units) are gaining more traction. Enhanced AI capabilities on commodity x86 architectures are commercially appealing due to the reuse of existing hardware and virtualization ease. A notable work in this direction is the SLIDE system. SLIDE is...