A5009123796- Complex Systems and Time Series Analysis
- Economic theories and models
- Banking stability, regulation, efficiency
- Design Education and Practice
- Innovative Human-Technology Interaction
- Creativity in Education and Neuroscience
- Market Dynamics and Volatility
- Topic Modeling
- Innovation Diffusion and Forecasting
- Monetary Policy and Economic Impact
- Software Engineering Research
- Machine Learning in Materials Science
École Polytechnique
2023-2024
Technical University of Munich
2024
Centre National de la Recherche Scientifique
2023
Laboratoire d'Hydrodynamique
2023
Laboratoire d'Informatique de l'École Polytechnique
2023
Previous efforts to support creative problem-solving have included (a) techniques (such as brainstorming and design thinking) stimulate ideas, (b) software tools record share these ideas. Now, generative AI technologies can suggest new ideas that might never occurred the users, users then select from or use them even more Here, we describe such a system, Supermind Ideator. The system uses large language model (GPT 3.5) adds prompting, fine tuning, user interface specifically designed help...
Previous efforts to support creative problem-solving have included (a) techniques such as brainstorming and design thinking stimulate ideas, (b) software tools record share these ideas. Now, generative AI technologies can suggest new ideas that might never occurred the users, users then select from or use them even more To explore possibilities, we developed a system called Supermind Ideator uses large language model (LLM) adds prompts, fine tuning, specialized user interface in order help...
Agent-Based Models (ABM) are computational scenario-generators, which can be used to predict the possible future outcomes of complex system they represent. To better understand robustness these predictions, it is necessary full scope phenomena model generate. Most often, due high-dimensional parameter spaces, this a computationally expensive task. Inspired by ideas coming from systems biology, we show that for multiple macroeconomic models, including an agent-based and several Dynamic...
The economic shocks that followed the COVID-19 pandemic have brought to light difficulty, both for academics and policy makers, of describing predicting dynamics inflation. This paper offers an alternative modelling approach. We study 2020-2023 period within well-studied Mark-0 Agent-Based Model, in which agents act react according plausible behavioural rules. include particular a mechanism through trust Central Bank can de-anchor. investigate influence regulatory policies on inflationary...
The economic shocks that followed the COVID-19 pandemic have brought to light difficulty, both for academics and policy makers, of describing predicting dynamics inflation. This paper offers an alternative modelling approach. We study 2020-2023 period within well-studied Mark-0 Agent-Based Model, in which agents act react according plausible behavioural rules. include a mechanism through trust Central Bank can de-anchor. investigate influence regulatory policies on inflationary resulting...
Agent-Based Models (ABM) are computational scenario-generators, which can be used to predict the possible future outcomes of complex system they represent. To better understand robustness these predictions, it is necessary full scope phenomena model generate. Most often, due high-dimensional parameter spaces, this a computationally expensive task. Inspired by ideas coming from systems biology, we show that for multiple macroeconomic models, including an agent-based and several Dynamic...