Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field

Posted by dbos Harvard

Kavli Affiliate: Daniel Needleman | First 5 Authors: Stanislav Lukyanenko, Won-Dong Jang, Donglai Wei, Robbert Struyven, Yoon Kim | Summary: The developmental process of embryos follows a monotonic order. An embryo can progressively cleave from one cell to multiple cells and finally transform to morula and blastocyst. For time-lapse videos of embryos, most existing developmental […]


Continue.. Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field

Learning intermolecular forces at liquid-vapor interfaces

Posted by klaurent Berkeley

Kavli Affiliate: David T. Limmer | First 5 Authors: Samuel P. Niblett, Mirza Galib, David T. Limmer, , | Summary: By adopting a perspective informed by contemporary liquid state theory, we consider how to train an artificial neural network potential to describe inhomogeneous, disordered systems. We find that neural network potentials based on local representations […]


Continue.. Learning intermolecular forces at liquid-vapor interfaces

Quasiparticle kinetic theory for Calogero models

Posted by Berkeley

Kavli Affiliate: Joel E. Moore | First 5 Authors: Vir B. Bulchandani, Manas Kulkarni, Joel E. Moore, Xiangyu Cao, | Summary: We show that the quasiparticle kinetic theory for quantum and classical Calogero models reduces to the free-streaming Boltzmann equation. We reconcile this simple emergent behaviour with the strongly interacting character of the model by […]


Continue.. Quasiparticle kinetic theory for Calogero models

Ultra-low-noise Microwave to Optics Conversion in Gallium Phosphide

Posted by klaurent Delft

Kavli Affiliate: Simon Groblacher | First 5 Authors: Robert Stockill, Moritz Forsch, Frederick Hijazi, Grégoire Beaudoin, Konstantinos Pantzas | Summary: Mechanical resonators can act as excellent intermediaries to interface single photons in the microwave and optical domains due to their high quality factors. Nevertheless, the optical pump required to overcome the large energy difference between […]


Continue.. Ultra-low-noise Microwave to Optics Conversion in Gallium Phosphide

Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases

Posted by klaurent Harvard

Kavli Affiliate: Michael P. Brenner | First 5 Authors: Subhashini Venugopalan, Joel Shor, Manoj Plakal, Jimmy Tobin, Katrin Tomanek | Summary: Automatic classification of disordered speech can provide an objective tool for identifying the presence and severity of speech impairment. Classification approaches can also help identify hard-to-recognize speech samples to teach ASR systems about the […]


Continue.. Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases

A representation-independent electronic charge density database for crystalline materials

Posted by klaurent Berkeley

Kavli Affiliate: Kristin A. Persson | First 5 Authors: Jimmy-Xuan Shen, Jason M. Munro, Matthew K. Horton, Patrick Huck, Shyam Dwaraknath | Summary: In addition to being the core quantity in density functional theory, the charge density can be used in many tertiary analyses in materials sciences from bonding to assigning charge to specific atoms. […]


Continue.. A representation-independent electronic charge density database for crystalline materials

A Compact Survey on Event Extraction: Approaches and Applications

Posted by klaurent Caltech

Kavli Affiliate: Lihong Wang | First 5 Authors: Qian Li, Jianxin Li, Jiawei Sheng, Shiyao Cui, Jia Wu | Summary: Event extraction is a critical technique to apprehend the essential content of events promptly. With the rapid development of deep learning technology, event extraction technology based on deep learning has become a research hotspot. Numerous […]


Continue.. A Compact Survey on Event Extraction: Approaches and Applications

Tunable strong coupling of mechanical resonance between spatially separated FePS$_3$ nanodrums

Posted by klaurent Delft

Kavli Affiliate: Herre S. J. Van Der Zant | First 5 Authors: Makars Šiškins, Ekaterina Sokolovskaya, Martin Lee, Samuel Mañas-Valero, Dejan Davidovikj | Summary: Coupled nanomechanical resonators made of two-dimensional materials are promising for processing information with mechanical modes. However, the challenge for these types of systems is to control the coupling. Here, we demonstrate […]


Continue.. Tunable strong coupling of mechanical resonance between spatially separated FePS$_3$ nanodrums

High conductivity Polarization-induced 2D hole gases in Undoped GaN/AlN Heterojunctions enabled by Impurity Blocking Layers

Posted by Cornell

Kavli Affiliate: Grace Xing | First 5 Authors: Reet Chaudhuri, Zhen Chen, David Muller, Huili Grace Xing, Debdeep Jena | Summary: High-conductivity undoped GaN/AlN 2D hole gases (2DHGs), the p-type dual of the AlGaN/GaN 2D electron gases (2DEGs), have offered valuable insights into hole transport in GaN and enabled the first GaN GHz RF p-channel […]


Continue.. High conductivity Polarization-induced 2D hole gases in Undoped GaN/AlN Heterojunctions enabled by Impurity Blocking Layers

Improving Transferability of Adversarial Patches on Face Recognition with Generative Models

Posted by klaurent Caltech

Kavli Affiliate: Wei Gao | First 5 Authors: Zihao Xiao, Xianfeng Gao, Chilin Fu, Yinpeng Dong, Wei Gao | Summary: Face recognition is greatly improved by deep convolutional neural networks (CNNs). Recently, these face recognition models have been used for identity authentication in security sensitive applications. However, deep CNNs are vulnerable to adversarial patches, which […]


Continue.. Improving Transferability of Adversarial Patches on Face Recognition with Generative Models