1 code implementation • 6 Dec 2023 • Shiro Takagi
This paper engages in a speculative exploration of the concept of an artificial agent capable of conducting research.
no code implementations • 16 Nov 2023 • Shiro Takagi, Ryutaro Yamauchi, Wataru Kumagai
Research automation efforts usually employ AI as a tool to automate specific tasks within the research process.
2 code implementations • 17 Nov 2022 • Shiro Takagi
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.
1 code implementation • 15 Nov 2022 • Hiroki Naganuma, Kartik Ahuja, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, Ikuro Sato, Ioannis Mitliagkas
Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution.
no code implementations • 26 Apr 2022 • Yasuhiko Asao, Ryotaro Sakamoto, Shiro Takagi
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.
no code implementations • 6 Sep 2021 • Yasuhiko Asao, Jumpei Nagase, Ryotaro Sakamoto, Shiro Takagi
By considering this weighted graph as a pseudo-metric space, we construct a Vietoris-Rips complex with a parameter $\varepsilon$ by a well-known process of algebraic topology.
no code implementations • 16 May 2021 • Haruka Asanuma, Shiro Takagi, Yoshihiro Nagano, Yuki Yoshida, Yasuhiko Igarashi, Masato Okada
Teacher-student learning is a framework in which we introduce two neural networks: one neural network is a target function in supervised learning, and the other is a learning neural network.
no code implementations • 25 Sep 2019 • Shiro Takagi, Yoshihiro Nagano, Yuki Yoshida, Masato Okada
Model-agnostic meta-learning (MAML) is known as a powerful meta-learning method.
no code implementations • 25 Sep 2019 • Yoshihiro Nagano, Shiro Takagi, Yuki Yoshida, Masato Okada
The local learning approach extracts semantic representations for these datasets by training the embedding model from scratch for each local neighborhood, respectively.