| 研究課題/領域番号 |
22K20679
|
|---|
| 研究種目 |
研究活動スタート支援
|
| 配分区分 | 基金 |
|---|
| 審査区分 |
0704:神経科学、ブレインサイエンスおよびその関連分野
|
|---|
| 研究機関 | 東京大学 |
|---|
研究代表者 |
チャン ユーチャン 東京大学, 大学院工学系研究科(工学部), 特任助教 (50831484)
|
|---|
| 研究期間 (年度) |
2022-08-31 – 2024-03-31
|
| 研究課題ステータス |
交付 (2022年度)
|
| 配分額 *注記 |
2,730千円 (直接経費: 2,100千円、間接経費: 630千円)
2023年度: 1,300千円 (直接経費: 1,000千円、間接経費: 300千円)
2022年度: 1,430千円 (直接経費: 1,100千円、間接経費: 330千円)
|
|---|
| キーワード | Consciousness / ICT / Mathematical Model / Neural Systems / Sense of Agency / Artificial Intelligence / Scale Problem / Simulation / information closure / Conscious Action |
|---|
| 研究開始時の研究の概要 |
This project investigates conscious action and the sense of agency using the framework of the Information Closure Theory of consciousness. Research aims include understanding the sense of agency via information theory and identifying conscious action and agency in neural and artificial systems.
|
| 研究実績の概要 |
Research Update: We have successfully navigated the first phase of our project, establishing mathematical foundations of conscious self and agency within the Information Closure Theory (ICT) framework. By hypothesizing informational closure (IC) and non-trivial informational closure (NTIC), we've begun to understand how consciousness might be scale-dependent within the neural system. The second phase, presently underway, involves small-scale simulations. Early results are promising, with artificial agents displaying potential NTIC processes post-training. We're working diligently to determine if these processes encode not only environmental data but also information about the system's partition and action states. If successful, these results will provide a critical step towards applying our refined ICT framework to leading artificial systems in phase three, thereby contributing significantly to both neuroscience and ethical discussions in AI research.
In addition to our progress in the first two phases, we've also made several significant breakthroughs in terms of the practical implications of our research. We've identified key neuroscientific insights that could have a profound impact on our understanding of the human brain and consciousness, and we've also uncovered potential ethical implications of our work with AI systems.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
Our project is progressing well, following the established timeline. Phase 1, which involved the development of a mathematical model within the Information Closure Theory (ICT) framework, was completed successfully. In Phase 2, we conducted small-scale simulations and observed promising results, indicating the model's potential to capture conscious self and agency. As we transition into Phase 3, we will apply the ICT framework to leading artificial agents. Despite the complexity of the research, we've experienced no significant delays, affirming the project's smooth progression. We anticipate valuable insights in both neuroscience and AI ethics.
|
| 今後の研究の推進方策 |
Moving into the second half of the project, our focus shifts to Phase 3, where we'll apply the newly developed ICT framework to leading AI systems. We'll measure conscious self and agency in these systems, a critical step in validating our model. This phase involves developing empirical measures for systems with large numbers of elements, an aspect essential for both AI and neurophysiological data analysis. We anticipate potential challenges due to the complexity of advanced AI systems, but we're well-equipped to tackle them. The findings from this phase will provide key insights into consciousness in different anatomical systems, benefiting neuroscience and AI ethics.
|
