2022 Fiscal Year Research-status Report
Reveal the informational nature of conscious self and sense of agency under the information closure theory of consciousness
| Project/Area Number |
22K20679
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
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)
|
|---|
| Project Period (FY) |
2022-08-31 – 2024-03-31
|
| Keywords | Consciousness / ICT / Mathematical Model / Neural Systems / Sense of Agency / Artificial Intelligence / Scale Problem / Simulation |
|---|
| Outline of Annual Research Achievements |
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.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
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.
|
| Strategy for Future Research Activity |
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.
|
| Causes of Carryover |
For next year's research budget, we have 2,369,872 yen at our disposal. Our proposed plan includes the purchase of a GPU-powered workstation, which we estimate will cost approximately 1,000,000 yen. This is a crucial investment in our research, as it will provide us with the computational power necessary to conduct our simulations and analyze our data effectively. In addition, we plan to attend an international conference to share our findings with other researchers in the field and collaborate on new ideas. To cover travel, accommodation, and registration expenses, we will allocate approximately 600,000 yen towards this event.
We also anticipate the need for personal expenses, such as research materials and equipment, which we have budgeted at 300,000 yen. Finally, we plan to attend and present at several domestic conferences throughout the year to share our progress and receive feedback from other researchers. We will allocate the remaining funds to cover expenses related to these events, which we estimate will be approximately 469,872 yen. We believe we can make the most of our available budget and continue to make progress towards our research goals.
|
