To overcome this bottleneck, we propose a robust architecture that employs a computational memory unit as the explicit memory performing analog in-memory computation on high-dimensional (HD) vectors, while closely matching 32-bit software-equivalent accuracy. This is achieved by a content-based ...
Machine learning potentials have become an important tool for atomistic simulations in many fields, from chemistry via molecular biology to materials science. Most of the established methods, however, rely on local properties and are thus unable to take
"High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction"IEEE Transactions on Pattern Analysis and Machine Intelligence,Nan Meng, Hayden K-H. So, Xing Sun, Edmund Y. Lam, 2019.[Paper] "High-order Residual Network for Light Field Super-Resolution"The 34th AAAI ...
Neural networks offer an unbiased and numerically very accurate approach to represent high-dimensionalab initiopotential-energy surfaces. Once constructed, neural network potentials can provide the energies and forces many orders of magnitude faster than electronic structure calculations, and thus enable mole...
dimensional problems such as 3D perception, registration, and statistical data. We define neural networks specialized for these inputs assparse tensor networksand these sparse tensor networks process and generate sparse tensors as outputs. To construct a sparse tensor network, we build all standard ...
seeking scalability and robustness in high-dimensional and complex scenarios [36,54]. Crucially, the use of artificial neural networks offers the promise of accurate and efficient function approximation which in conjunction with Monte Carlo methods might beat thecurse of dimensionality, as investigated ...
We consider the problem of high-dimensional light field reconstruction and develop a learning-based framework for spatial and angular super-resolution. Many current approaches either require disparity clues or restore the spatial and angular details separately. Such methods have difficulties with non-Lambe...
Unlimited high-dimensional sparse tensor support All standard neural network layers (Convolution, Pooling, Broadcast, etc.) Dynamic computation graph Custom kernel shapes Multi-GPU training Multi-threaded kernel map Multi-threaded compilation Highly-optimized GPU kernels ...
Deep feature screening: Feature selection for ultra high-dimensional data via deep neural networks The applications of traditional statistical feature selection methods to high-dimension, low-sample-size data often struggle and encounter challenging prob... K Li,F Wang,L Yang,... - 《Neurocomputing...
We demonstrate its efficacy to parameterize potential models (physics based and high-dimensional neural networks) for 54 different elemental systems across the periodic table as well as alloys. We analyze error trends across different elements in the latent space and trace their origin to elemental ...