Results 81 to 90 of about 224,776 (267)

BLNN: An R package for training neural networks using Bayesian inference

SoftwareX, 2020
The Bayesian Learning for Neural Networks (BLNN) package coalesces the predictive power of neural networks with a breadth of Bayesian sampling techniques for the first time in R.
Taysseer Sharaf, Theren Williams, Abdallah Chehade, Keshav Pokhrel   +3 more
doaj   +1 more source

Continual Learning for Multimodal Data Fusion of a Soft Gripper

Advanced Robotics Research, EarlyView.
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley   +1 more source

Efficient Scaling of Bayesian Neural Networks

IEEE Access
While Bayesian neural networks (BNNs) have gained popularity for their theoretical guarantees and robustness, they have yet to see a convincing implementation at scale.
Jacob R. Epifano, Timothy Duong, Ravi P. Ramachandran, Ghulam Rasool   +3 more
doaj   +1 more source

Flat Seeking Bayesian Neural Networks

, 2023
Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior distribution based on observed data. The model sampled from the posterior distribution can be used for providing ensemble predictions and quantifying prediction uncertainty.
Nguyen, Van-Anh, Vuong, Tung-Long, Phan, Hoang, Do, Thanh-Toan, Phung, Dinh, Le, Trung   +5 more
openaire   +2 more sources

Compliant Pneumatic Feet with Real‐Time Stiffness Adaptation for Humanoid Locomotion

Advanced Robotics Research, EarlyView.
A compliant pneumatic foot with real‐time variable stiffness enables humanoid robots to adapt to changing terrains. Using onboard vision and pressure control, the foot modulates stiffness within each gait cycle, reducing impact forces and improving balance. The design, cast in soft silicone with embedded air chambers and Kevlar wrapping, offers durable,
Irene Frizza, Hiroshi Kaminaga, Philippe Fraisse, Gentiane Venture   +3 more
wiley   +1 more source

Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets

, 2017
Bayesian optimization has become a successful tool for hyperparameter optimization of machine learning algorithms, such as support vector machines or deep neural networks.
Bartels, Simon, Falkner, Stefan, Hennig, Philipp, Hutter, Frank, Klein, Aaron   +4 more
core  

CellPolaris: Transfer Learning for Gene Regulatory Network Construction to Guide Cell State Transitions

Advanced Science, EarlyView.
CellPolaris decodes how transcription factors guide cell fate by building gene regulatory networks from transcriptomic data using transfer learning. It generates tissue‐ and cell‐type‐specific networks, identifies master regulators in cell state transitions, and simulates TF perturbations in developmental processes.
Guihai Feng, Xin Qin, Jiahao Zhang, Wuliang Huang, Yiyang Zhang, Wentao Cui, Yao Chen, Shirui Li, Wenhao Liu, Yao Tian, Yana Liu, Jingxi Dong, Ping Xu, Zhenpeng Man, Guole Liu, Zhongming Liang, Xinlong Jiang, Xiaodong Yang, Pengfei Wang, Ge Yang, Hongmei Wang, Xuezhi Wang, Ming‐Han Tong, Yuanchun Zhou, Shihua Zhang, Yiqiang Chen, Yong Wang, Xin Li   +27 more
wiley   +1 more source

Modeling Breast Cancer Using Data Mining Methods

مجله انفورماتیک سلامت و زیست پزشکی, 2018
Introduction: Breast cancer is the most common form of cancer in women. Breast cancer detection is considered as one of the most important issues in medical science.
Parvaneh Dehghan, Maedeh Mogharabi, Iman Zabbah, Kamran Layeghi, Ali Maroosi   +4 more
doaj  

CLinNET: An Interpretable and Uncertainty‐Aware Deep Learning Framework for Multi‐Modal Clinical Genomics

Advanced Science, EarlyView.
Identifying disease‐causing genes in neurocognitive disorders remains challenging due to variants of uncertain significance. CLinNET employs dual‐branch neural networks integrating Reactome pathways and Gene Ontology terms to provide pathway‐level interpretability of genomic alterations.
Ivan Bakhshayeshi, Mohammad Mahdi Hosseini, Ahmadreza Argha, Roxana Zahedi, Nigel H. Lovell, Hamid Alinejad‐Rokny   +5 more
wiley   +1 more source

DualPG‐DTA: A Large Language Model‐Powered Graph Neural Network Framework for Enhanced Drug‐Target Affinity Prediction and Discovery of Novel CDK9 Inhibitors Exhibiting in Vivo Anti‐Leukemia Activity

Advanced Science, EarlyView.
This study introduces DualPG‐DTA, a framework integrating two pre‐trained models to generate molecular and protein representations. It constructs dual graphs processed by specialized neural networks with dynamic attention for feature fusion, achieving superior benchmark performance.
Yihao Chen, Jindi Huang, Cong Liu, Shipeng Zhang, Xinze Li, Zhang Zhang, Tie‐Gen Chen, Ling Wang   +7 more
wiley   +1 more source