no code implementations • 15 Apr 2024 • Taichi Sakaguchi, Akira Taniguchi, Yoshinobu Hagiwara, Lotfi El Hafi, Shoichi Hasegawa, Tadahiro Taniguchi
To address this, we propose a novel method called Few-shot Cross-quality Instance-aware Adaptation (CrossIA), which employs contrastive learning with an instance classifier to align features between massive low- and few high-quality images.
1 code implementation • 8 Nov 2023 • Ryo Ueda, Tadahiro Taniguchi
As a sub-discipline of evolutionary and computational linguistics, emergent communication (EC) studies communication protocols, called emergent languages, arising in simulations where agents communicate.
no code implementations • 8 Sep 2023 • Hiroki Nakamura, Masashi Okada, Tadahiro Taniguchi
Moreover, experiments on image retrieval using MNIST and PascalVOC showed that the representations of our method can be operated by OR and AND operations.
no code implementations • 11 Jul 2023 • Tomoaki Nakamura, Akira Taniguchi, Tadahiro Taniguchi
Therefore, the agents change their actions according to the estimated messages to achieve cooperative tasks.
no code implementations • 27 Jun 2023 • Yoshinobu Hagiwara, Kazuma Furukawa, Takafumi Horie, Akira Taniguchi, Tadahiro Taniguchi
We present a computational model for a symbol emergence system that enables the emergence of lexical knowledge with combinatoriality among agents through a Metropolis-Hastings naming game and cross-situational learning.
no code implementations • 31 May 2023 • Ryota Okumura, Tadahiro Taniguchi, Yosinobu Hagiwara, Akira Taniguchi
By comparing human acceptance decisions of a partner's naming with acceptance probabilities computed in the MHNG, we tested whether human behavior is consistent with the MHNG theory.
no code implementations • 31 May 2023 • Jun Inukai, Tadahiro Taniguchi, Akira Taniguchi, Yoshinobu Hagiwara
The main contributions of this paper are twofold: (1) we propose the recursive Metropolis-Hastings naming game (RMHNG) as an N-agent version of MHNG and demonstrate that RMHNG is an approximate Bayesian inference method for the posterior distribution over a latent variable shared by agents, similar to MHNG; and (2) we empirically evaluate the performance of RMHNG on synthetic and real image data, enabling multiple agents to develop and share a symbol system.
no code implementations • 14 Jan 2023 • Tadahiro Taniguchi, Shingo Murata, Masahiro Suzuki, Dimitri Ognibene, Pablo Lanillos, Emre Ugur, Lorenzo Jamone, Tomoaki Nakamura, Alejandra Ciria, Bruno Lara, Giovanni Pezzulo
Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics.
no code implementations • 20 Nov 2022 • Akira Taniguchi, Yoshiki Tabuchi, Tomochika Ishikawa, Lotfi El Hafi, Yoshinobu Hagiwara, Tadahiro Taniguchi
This study provides insights into the technical aspects of the proposed method, including active perception and exploration by the robot, and how the method can enable mobile robots to learn spatial concepts through active exploration.
no code implementations • 6 Jul 2022 • Akira Taniguchi, Maoko Muro, Hiroshi Yamakawa, Tadahiro Taniguchi
This study proposes a PGM for a DAA hypothesis that can be realized in the brain based on the outcomes of several neuroscientific surveys.
1 code implementation • 9 Jun 2022 • Kohei Suzuki, Shoki Sakamoto, Tadahiro Taniguchi, Hirokazu Kameoka
This paper proposes a new voice conversion (VC) task from human speech to dog-like speech while preserving linguistic information as an example of human to non-human creature voice conversion (H2NH-VC) tasks.
1 code implementation • 24 May 2022 • Tadahiro Taniguchi, Yuto Yoshida, Akira Taniguchi, Yoshinobu Hagiwara
Instead, it is a game based on joint attention without explicit feedback.
no code implementations • 24 May 2022 • Kazuma Furukawa, Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi
On the basis of the H2H-type Inter-MDM, we propose a naming game in the same way as the conventional Inter-MDM.
no code implementations • ICCV 2023 • Hiroki Nakamura, Masashi Okada, Tadahiro Taniguchi
In this study, a novel self-supervised learning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties.
1 code implementation • 21 Mar 2022 • Akira Taniguchi, Shuya Ito, Tadahiro Taniguchi
Navigation experiments using speech instruction with a waypoint demonstrated the performance improvement of path planning, WN-SPL by 0. 589, and reduced computation time by 7. 14 sec compared to conventional methods.
no code implementations • 15 Mar 2022 • Akira Kinose, Masashi Okada, Ryo Okumura, Tadahiro Taniguchi
In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming.
no code implementations • 10 Mar 2022 • Ryo Okumura, Nobuki Nishio, Tadahiro Taniguchi
An industrial connector insertion task requires submillimeter positioning and grasp pose compensation for a plug.
no code implementations • 1 Mar 2022 • Masashi Okada, Tadahiro Taniguchi
The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming.
1 code implementation • 18 Jan 2022 • Akira Taniguchi, Hiroaki Murakami, Ryo Ozaki, Tadahiro Taniguchi
The proposed method can acquire words and phonemes from speech signals using unsupervised learning and utilize object information based on multiple modalities-vision, tactile, and auditory-simultaneously.
no code implementations • 15 Sep 2021 • Yoshinobu Hagiwara, Kazuma Furukawa, Akira Taniguchi, Tadahiro Taniguchi
(2) Function to improve the categorization accuracy in an agent via semiotic communication with another agent, even when some sensory modalities of each agent are missing.
no code implementations • 10 Aug 2021 • Shoki Sakamoto, Akira Taniguchi, Tadahiro Taniguchi, Hirokazu Kameoka
Although this method is powerful, it can fail to preserve the linguistic content of input speech when the number of available training samples is extremely small.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 16 Jun 2021 • Rikunari Sagara, Ryo Taguchi, Akira Taniguchi, Tadahiro Taniguchi, Koosuke Hattori, Masahiro Hoguro, Taizo Umezaki
The experimental results show that relative spatial concepts and a phoneme sequence representing each concept can be learned under the condition that the robot does not know which located object is the reference object.
no code implementations • 5 Apr 2021 • Asuka Moritani, Ryo Ozaki, Shoki Sakamoto, Hirokazu Kameoka, Tadahiro Taniguchi
Through subjective evaluation experiments, we evaluated the performance of our StarGAN-EVC system in terms of its ability to achieve EVC for Japanese phrases.
no code implementations • 16 Mar 2021 • Yuki Katsumata, Akinori Kanechika, Akira Taniguchi, Lotfi El Hafi, Yoshinobu Hagiwara, Tadahiro Taniguchi
Using the spatial structure of various indoor environments as prior knowledge, the robot would construct the map more efficiently.
1 code implementation • 15 Mar 2021 • Yasuaki Okuda, Ryo Ozaki, Tadahiro Taniguchi
The main contributions of this study are as follows: 1) We develop a probabilistic generative model for time series data including prosody that potentially has a double articulation structure; 2) We propose the Prosodic DAA by deriving the inference procedure for Prosodic HDP-HLM and show that Prosodic DAA can discover words directly from continuous human speech signals using statistical information and prosodic information in an unsupervised manner; 3) We show that prosodic cues contribute to word segmentation more in naturally distributed case words, i. e., they follow Zipf's law.
no code implementations • 15 Mar 2021 • Tadahiro Taniguchi, Hiroshi Yamakawa, Takayuki Nagai, Kenji Doya, Masamichi Sakagami, Masahiro Suzuki, Tomoaki Nakamura, Akira Taniguchi
This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model(PGM)-based cognitive system to develop a cognitive system for developmental robots by integrating PGMs.
no code implementations • 11 Mar 2021 • Yoshinobu Hagiwara, Keishiro Taguchi, Satoshi Ishibushi, Akira Taniguchi, Tadahiro Taniguchi
This paper proposes a hierarchical Bayesian model based on spatial concepts that enables a robot to transfer the knowledge of places from experienced environments to a new environment.
no code implementations • 29 Jul 2020 • Masashi Okada, Tadahiro Taniguchi
In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels.
no code implementations • 1 Mar 2020 • Masashi Okada, Norio Kosaka, Tadahiro Taniguchi
In this paper, we extend VI-MPC and PaETS, which have been originally introduced in previous literature, to address partially observable cases.
1 code implementation • 18 Feb 2020 • Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi, Tetsunari Inamura
The aim of this study is to enable a mobile robot to perform navigational tasks with human speech instructions, such as `Go to the kitchen', via probabilistic inference on a Bayesian generative model using spatial concepts.
no code implementations • 10 Feb 2020 • Akira Taniguchi, Shota Isobe, Lotfi El Hafi, Yoshinobu Hagiwara, Tadahiro Taniguchi
We evaluate the effectiveness of the proposed method by an experimental simulation that reproduces the conditions of the Tidy Up Here task of the World Robot Summit 2018 international robotics competition.
no code implementations • 31 Jan 2020 • Ryo Okumura, Masashi Okada, Tadahiro Taniguchi
We experimentally evaluated the model predictive control performance via imitation learning for continuous control of sparse reward tasks in simulators and compared it with the performance of the existing SRL method.
no code implementations • 20 Oct 2019 • Tadahiro Taniguchi, Tomoaki Nakamura, Masahiro Suzuki, Ryo Kuniyasu, Kaede Hayashi, Akira Taniguchi, Takato Horii, Takayuki Nagai
The model is called VAE+GMM+LDA+ASR.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 16 Sep 2019 • Masashi Okada, Shinji Takenaka, Tadahiro Taniguchi
An important component of SMC, i. e., a proposal distribution, is designed as a probabilistic neural pose predictor, which can propose diverse and plausible hypotheses by incorporating epistemic uncertainty and heteroscedastic aleatoric uncertainty.
no code implementations • 8 Jul 2019 • Masashi Okada, Tadahiro Taniguchi
Probabilistic ensembles with trajectory sampling (PETS) is a leading type of MBRL, which employs Bayesian inference to dynamics modeling and model predictive control (MPC) with stochastic optimization via the cross entropy method (CEM).
no code implementations • 3 Jul 2019 • Akira Kinose, Tadahiro Taniguchi
In this paper, we present a new theory for integrating reinforcement and imitation learning by extending the probabilistic generative model framework for reinforcement learning, {\it plan by inference}.
no code implementations • 31 May 2019 • Yoshinobu Hagiwara, Hiroyoshi Kobayashi, Akira Taniguchi, Tadahiro Taniguchi
In this paper, we describe a new computational model that represents symbol emergence in a two-agent system based on a probabilistic generative model for multimodal categorization.
no code implementations • 12 Dec 2018 • Amir Aly, Tadahiro Taniguchi
Robots are widely collaborating with human users in diferent tasks that require high-level cognitive functions to make them able to discover the surrounding environment.
3 code implementations • 9 Mar 2018 • Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi, Tetsunari Inamura
We propose a novel online learning algorithm, called SpCoSLAM 2. 0, for spatial concepts and lexical acquisition with high accuracy and scalability.
no code implementations • 26 Jan 2018 • Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Oztop, Justus Piater, Florentin Wörgötter
However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered.
1 code implementation • 4 Dec 2017 • Tomoaki Nakamura, Takayuki Nagai, Tadahiro Taniguchi
Experimental results demonstrated that the model can be constructed by connecting modules, the parameters can be optimized as a whole, and they are comparable with the original models that we have proposed.
5 code implementations • 15 Apr 2017 • Akira Taniguchi, Yoshinobu Hagiwara, Tadahiro Taniguchi, Tetsunari Inamura
We have proposed a nonparametric Bayesian spatial concept acquisition model (SpCoA).
no code implementations • 3 Feb 2016 • Akira Taniguchi, Tadahiro Taniguchi, Tetsunari Inamura
In this paper, we propose a novel unsupervised learning method for the lexical acquisition of words related to places visited by robots, from human continuous speech signals.
1 code implementation • 1 Oct 2015 • Tadahiro Taniguchi, Toshiaki Takano, Ryo Yoshino
We propose an MHDP-based active perception method that uses the information gain (IG) maximization criterion and lazy greedy algorithm.
no code implementations • 29 Sep 2015 • Tadahiro Taniguchi, Takayuki Nagai, Tomoaki Nakamura, Naoto Iwahashi, Tetsuya OGATA, Hideki Asoh
Humans can learn the use of language through physical interaction with their environment and semiotic communication with other people.
no code implementations • 22 Jun 2015 • Tadahiro Taniguchi, Ryo Nakashima, Shogo Nagasaka
In this paper, we develop a novel machine learning method called nonparametric Bayesian double articulation analyzer (NPB-DAA) that can directly acquire language and acoustic models from observed continuous speech signals.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4