Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Akiba, Takuya"'
Training large language models to acquire specific skills remains a challenging endeavor. Conventional training approaches often struggle with data distribution imbalances and inadequacies in objective functions that do not align well with task-speci
Externí odkaz:
http://arxiv.org/abs/2410.14735
We present a novel application of evolutionary algorithms to automate the creation of powerful foundation models. While model merging has emerged as a promising approach for LLM development due to its cost-effectiveness, it currently relies on human
Externí odkaz:
http://arxiv.org/abs/2403.13187
Autor:
Niitani, Yusuke, Ogawa, Toru, Suzuki, Shuji, Akiba, Takuya, Kerola, Tommi, Ozaki, Kohei, Sano, Shotaro
We present the instance segmentation and the object detection method used by team PFDet for Open Images Challenge 2019. We tackle a massive dataset size, huge class imbalance and federated annotations. Using this method, the team PFDet achieved 3rd a
Externí odkaz:
http://arxiv.org/abs/1910.11534
Autor:
Tokui, Seiya, Okuta, Ryosuke, Akiba, Takuya, Niitani, Yusuke, Ogawa, Toru, Saito, Shunta, Suzuki, Shuji, Uenishi, Kota, Vogel, Brian, Vincent, Hiroyuki Yamazaki
Software frameworks for neural networks play a key role in the development and application of deep learning methods. In this paper, we introduce the Chainer framework, which intends to provide a flexible, intuitive, and high performance means of impl
Externí odkaz:
http://arxiv.org/abs/1908.00213
The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that allows users to construct the parameter search space dynamically, (2) e
Externí odkaz:
http://arxiv.org/abs/1907.10902
Recomputation algorithms collectively refer to a family of methods that aims to reduce the memory consumption of the backpropagation by selectively discarding the intermediate results of the forward propagation and recomputing the discarded results a
Externí odkaz:
http://arxiv.org/abs/1905.11722
Efficient and reliable methods for training of object detectors are in higher demand than ever, and more and more data relevant to the field is becoming available. However, large datasets like Open Images Dataset v4 (OID) are sparsely annotated, and
Externí odkaz:
http://arxiv.org/abs/1811.10862
We present a large-scale object detection system by team PFDet. Our system enables training with huge datasets using 512 GPUs, handles sparsely verified classes, and massive class imbalance. Using our method, we achieved 2nd place in the Google AI Op
Externí odkaz:
http://arxiv.org/abs/1809.00778
Autor:
Kurakin, Alexey, Goodfellow, Ian, Bengio, Samy, Dong, Yinpeng, Liao, Fangzhou, Liang, Ming, Pang, Tianyu, Zhu, Jun, Hu, Xiaolin, Xie, Cihang, Wang, Jianyu, Zhang, Zhishuai, Ren, Zhou, Yuille, Alan, Huang, Sangxia, Zhao, Yao, Zhao, Yuzhe, Han, Zhonglin, Long, Junjiajia, Berdibekov, Yerkebulan, Akiba, Takuya, Tokui, Seiya, Abe, Motoki
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop ne
Externí odkaz:
http://arxiv.org/abs/1804.00097
Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently communicate grad
Externí odkaz:
http://arxiv.org/abs/1802.06058