Results 51 to 60 of about 141,062 (268)

Erythropoietin modulates hepatic inflammation, glucose homeostasis, and soluble epoxide hydrolase and epoxides in high‐fat diet‐induced obese mice

FEBS Open Bio, EarlyView.
Erythropoietin administration suppresses hepatic soluble epoxide hydrolase (sEH) expression, leading to increased CYP‐derived epoxides. This is associated with a shift in hepatic macrophage polarization characterized by reduced M1 markers and increased M2 markers, along with reduced hepatic inflammation, suppressed hepatic lipogenesis, and attenuated ...
Takeshi Goda, Satoru Sugimoto, Chiharu Cho, Madoka Konishi, Nozomi Inoue, Satoshi Miyagaki, Yasuhiro Kawabe, Takuro Okamura, Masahide Hamaguchi, Hisakazu Nakajima, Michiaki Fukui, Masakazu Shinohara, Tomoko Iehara   +12 more
wiley   +1 more source

Counterclockwise block-by-block knowledge distillation for neural network compression

Scientific Reports
Model compression is a technique for transforming large neural network models into smaller ones. Knowledge distillation (KD) is a crucial model compression technique that involves transferring knowledge from a large teacher model to a lightweight student
Xiaowei Lan, Yalin Zeng, Xiaoxia Wei, Tian Zhang, Yiwen Wang, Chao Huang, Weikai He   +6 more
doaj   +1 more source

Knowledge Distillation in Image Classification: The Impact of Datasets

Computers
As the demand for efficient and lightweight models in image classification grows, knowledge distillation has emerged as a promising technique to transfer expertise from complex teacher models to simpler student models.
Ange Gabriel Belinga, Cédric Stéphane Tekouabou Koumetio, Mohamed El Haziti, Mohammed El Hassouni   +3 more
doaj   +1 more source

Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons

, 2018
An activation boundary for a neuron refers to a separating hyperplane that determines whether the neuron is activated or deactivated. It has been long considered in neural networks that the activations of neurons, rather than their exact output values ...
Choi, Jin Young, Heo, Byeongho, Lee, Minsik, Yun, Sangdoo   +3 more
core   +1 more source

Elinvar Materials: Recent Progress and Challenges

Advanced Engineering Materials, EarlyView.
Elinvar materials, exhibiting temperature‐invariant elastic modulus, are critical for precision instruments and emerging technologies. This article reviews recent progress in the field, with a focus on the anomalous thermoelastic behavior observed in key material systems.
Wenjie Li, Yang Ren
wiley   +1 more source

Intermolecular Interactions as Driving Force of Increasing Multiphoton Absorption in a Perylene Diimide‐Based Coordination Polymer

Advanced Functional Materials, EarlyView.
This study uncovers the unexplored role of intermolecular interactions in multiphoton absorption in coordination polymers. By analyzing [Zn2tpda(DMA)2(DMF)0.3], it shows how the electronic coupling of the chromophores and confinement in the MOF enhance two‐and three‐photon absorption.
Simon Nicolas Deger, Anna Mauri, Yang Cui, Sebastian Josef Weishäupl, Ali Deniz Özdemir, Hamad Syed, Aleksandr Ovsianikov, Wolfgang Wenzel, Alexander Pöthig, Jürgen Hauer, Mariana Kozlowska, Roland Augustinus Fischer   +11 more
wiley   +1 more source

Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation

, 2019
Conventional automatic speech recognition (ASR) systems trained from frame-level alignments can easily leverage posterior fusion to improve ASR accuracy and build a better single model with knowledge distillation. End-to-end ASR systems trained using the
Audhkhasi, Kartik, Kurata, Gakuto
core   +1 more source

Relational Knowledge Distillation [PDF]

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher.
Park, Wonpyo, Kim, Dongju, Lu, Yan, Cho, Minsu   +3 more
openaire   +2 more sources

Unleashing the Power of Machine Learning in Nanomedicine Formulation Development

Advanced Functional Materials, EarlyView.
A random forest machine learning model is able to make predictions on nanoparticle attributes of different nanomedicines (i.e. lipid nanoparticles, liposomes, or PLGA nanoparticles) based on microfluidic formulation parameters. Machine learning models are based on a database of nanoparticle formulations, and models are able to generate unique solutions
Thomas L. Moore, Cristiano Pesce, Antonietta Greco, Claudia Pisante, Greta Avancini, Valentina Di Francesco, Yosi Shamay, Paolo Decuzzi   +7 more
wiley   +1 more source

Contrastive Learning‐Based Multi‐Level Knowledge Distillation

CAAI Transactions on Intelligence Technology
With the increasing constraints of hardware devices, there is a growing demand for compact models to be deployed on device endpoints. Knowledge distillation, a widely used technique for model compression and knowledge transfer, has gained significant ...
Lin Li, Jianping Gou, Weihua Ou, Wenbai Chen, Lan Du   +4 more
doaj   +1 more source