Position: It Is Time We Test Neural Computation In Vitro
Authors: Frithjof Gressmann, Ashley Chen, Lily Hexuan Xie, Nancy Amato, Lawrence Rauchwerger
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this position paper, we argue that this trend offers a unique and timely opportunity to put our understanding of neural computation to the test. By designing artificial neural networks that can interact and control living neural systems, it is becoming possible to validate computational models beyond simulation and gain empirical insights to help unlock more robust and energy-efficient next-generation AI systems. We provide an overview of key technologies, challenges, and principles behind this development and describe strategies and opportunities for novel machine learning research in this emerging field. |
| Researcher Affiliation | Academia | 1Siebel School of Computing and Data Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA. Correspondence to: Frithjof Gressmann <EMAIL>, Lawrence Rauchwerger <EMAIL>. |
| Pseudocode | No | The paper describes methods and problem formulations in narrative text, but it does not include any explicitly labeled pseudocode blocks or algorithms. |
| Open Source Code | No | The paper discusses the availability of open platforms and mentions other open-source projects (e.g., 'Spiking Jelly: An open-source machine learning infrastructure platform for spike-based intelligence' by Fang et al., 2023), but it does not provide any explicit statement or link for the open-sourcing of code specifically developed for the methodology described within this paper. |
| Open Datasets | No | The paper discusses concepts such as 'pre-recorded data' and 'synthetic data' in the context of training and refers to 'MNIST training' as a potential benchmark, but it does not specify any particular dataset used in its own research or provide access information for any open datasets. |
| Dataset Splits | No | The paper is a position paper and does not conduct empirical experiments, therefore no dataset split information is provided. |
| Hardware Specification | No | The paper discusses future hardware requirements for in vitro systems, such as 'custom FPGAs', and illustrates a 'commercial experimental in vitro system by Jordan et al. (2024)', but it does not specify any particular hardware used by the authors for experiments presented in this paper. |
| Software Dependencies | No | The paper refers to existing algorithms and simulation environments (e.g., 'Soft Actor-Critic (Haarnoja et al., 2019)' and 'Cleo (Johnsen et al., 2023)'), but it does not list specific software dependencies with version numbers for any methodology implemented by the authors. |
| Experiment Setup | No | The paper is a position paper that argues for a new research direction and conceptual framework; it does not describe specific experimental setups, hyperparameters, or training configurations for its own empirical work. |