Výsledky vyhledávání - "KITANO, Hiroaki"

Report

Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings

Autor: Akama, Taketo, Zhang, Zhuohao, Li, Pengcheng, Hongo, Kotaro, Kitano, Hiroaki, Minamikawa, Shun, Polouliakh, Natalia

Recent studies have demonstrated that the representations of artificial neural networks (ANNs) can exhibit notable similarities to cortical representations when subjected to identical auditory sensory inputs. In these studies, the ability to predict

Externí odkaz: http://arxiv.org/abs/2412.15560

Zobrazit plný text záznamu

Report

Naturalistic Music Decoding from EEG Data via Latent Diffusion Models

Autor: Postolache, Emilian, Polouliakh, Natalia, Kitano, Hiroaki, Connelly, Akima, Rodolà, Emanuele, Cosmo, Luca, Akama, Taketo

In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of reconstructing naturalistic music from electroencephalogram (EEG) recordings. Unlike simpler music with limited timbre

Externí odkaz: http://arxiv.org/abs/2405.09062

Zobrazit plný text záznamu

Report

The Future of Fundamental Science Led by Generative Closed-Loop Artificial Intelligence

Recent advances in machine learning and AI, including Generative AI and LLMs, are disrupting technological innovation, product development, and society as a whole. AI's contribution to technology can come from multiple approaches that require access

Externí odkaz: http://arxiv.org/abs/2307.07522

Zobrazit plný text záznamu

Report

Self-supervised Auxiliary Loss for Metric Learning in Music Similarity-based Retrieval and Auto-tagging

Autor: Akama, Taketo, Kitano, Hiroaki, Takematsu, Katsuhiro, Miyajima, Yasushi, Polouliakh, Natalia

In the realm of music information retrieval, similarity-based retrieval and auto-tagging serve as essential components. Given the limitations and non-scalability of human supervision signals, it becomes crucial for models to learn from alternative so

Externí odkaz: http://arxiv.org/abs/2304.07449

Zobrazit plný text záznamu

Report

Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report

Autor: Littman, Michael L., Ajunwa, Ifeoma, Berger, Guy, Boutilier, Craig, Currie, Morgan, Doshi-Velez, Finale, Hadfield, Gillian, Horowitz, Michael C., Isbell, Charles, Kitano, Hiroaki, Levy, Karen, Lyons, Terah, Mitchell, Melanie, Shah, Julie, Sloman, Steven, Vallor, Shannon, Walsh, Toby

In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society. It was written by a panel of 1

Externí odkaz: http://arxiv.org/abs/2210.15767

Zobrazit plný text záznamu