Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Takagi, Shiro"'
The progress in text summarization techniques has been remarkable. However the task of accurately extracting and summarizing necessary information from highly specialized documents such as research papers has not been sufficiently investigated. We ar
Externí odkaz:
http://arxiv.org/abs/2409.06883
This paper proposes a new conceptual framework called Collective Predictive Coding as a Model of Science (CPC-MS) to formalize and understand scientific activities. Building on the idea of collective predictive coding originally developed to explain
Externí odkaz:
http://arxiv.org/abs/2409.00102
Autor:
Takagi, Shiro
This paper engages in a speculative exploration of the concept of an artificial agent capable of conducting research. Initially, it examines how the act of research can be conceptually characterized, aiming to provide a starting point for discussions
Externí odkaz:
http://arxiv.org/abs/2312.03497
Research automation efforts usually employ AI as a tool to automate specific tasks within the research process. To create an AI that truly conduct research themselves, it must independently generate hypotheses, design verification plans, and execute
Externí odkaz:
http://arxiv.org/abs/2311.09706
Autor:
Takagi, Shiro
Publikováno v:
Advances in Neural Information Processing Systems 36 (NeurIPS 2022)
We empirically investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks. Analysis of the internal representation reveals
Externí odkaz:
http://arxiv.org/abs/2211.09817
Autor:
Naganuma, Hiroki, Ahuja, Kartik, Takagi, Shiro, Motokawa, Tetsuya, Yokota, Rio, Ishikawa, Kohta, Sato, Ikuro, Mitliagkas, Ioannis
Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution. While much promising work has been accomplished to address this fragility, a systematic study of the role of
Externí odkaz:
http://arxiv.org/abs/2211.08583
We give a proof that, under relatively mild conditions, fully-connected feed-forward deep random neural networks converge to a Gaussian mixture distribution as only the width of the last hidden layer goes to infinity. We conducted experiments for a s
Externí odkaz:
http://arxiv.org/abs/2204.12100
Extracting informative features from images has been of capital importance in computer vision. In this paper, we propose a way to extract such features from images by a method based on algebraic topology. To that end, we construct a weighted graph fr
Externí odkaz:
http://arxiv.org/abs/2109.02231
Autor:
Asanuma, Haruka, Takagi, Shiro, Nagano, Yoshihiro, Yoshida, Yuki, Igarashi, Yasuhiko, Okada, Masato
When a computational system continuously learns from an ever-changing environment, it rapidly forgets its past experiences. This phenomenon is called catastrophic forgetting. While a line of studies has been proposed with respect to avoiding catastro
Externí odkaz:
http://arxiv.org/abs/2105.07385
Autor:
Sakairi, Tetsuya, Okada, Miyoko, Ikeda, Itsuko, Utsumi, Hiroyuki, Kohge, Shin, Sugimoto, Jiro, Sano, Fumiko, Takagi, Shiro
Publikováno v:
In Experimental and Molecular Pathology 2007 83(3):419-427
