23 citations · 80 across the 22 of their papers we have counts for
4 papers · 1 filter
Data Cleansing for Deep Neural Networks with Storage-efficient Approximation of Influence Functions
Kenji Suzuki, Yoshiyuki Kobayashi, Takuya Narihira
Identifying the influence of training data for data cleansing can improve the accuracy of deep learning. An approach with stochastic gradient descent (SGD) called SGD-influence to…
Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives
Takuya Narihira, Javier Alonsogarcia, Fabien Cardinaux +14
While there exist a plethora of deep learning tools and frameworks, the fast-growing complexity of the field brings new demands and challenges, such as more flexible network design…
Out-of-core Training for Extremely Large-Scale Neural Networks With Adaptive Window-Based Scheduling
Akio Hayakawa, Takuya Narihira
While large neural networks demonstrate higher performance in various tasks, training large networks is difficult due to limitations on GPU memory size. We propose a novel out-of-c…
Fully Convolutional Search Heuristic Learning for Rapid Path Planners
Yuka Ariki, Takuya Narihira
Path-planning algorithms are an important part of a wide variety of robotic applications, such as mobile robot navigation and robot arm manipulation. However, in large search space…