Towards Regulated Deep Learning
Regulation of Multi-Agent Systems (MAS) and Declarative Electronic Institutions (DEIs) was a multidisciplinary research topic of the past decade involving (Physical and Software) Agents and Law since the beginning, but recently evolved towards News-claimed Robot Lawyer since 2016. One of these first proposals of restricting the behaviour of Software Agents was Electronic Institutions.However, with the recent reformulation of Artificial Neural Networks (ANNs) as Deep Learning (DL), Security, Privacy,Ethical and Legal issues regarding the use of DL has raised concerns in the Artificial Intelligence (AI) Community. Now that the Regulation of MAS is almost correctly addressed, we propose the Regulation of Artificial Neural Networks as Agent-based Training of a special type of regulated Artificial Neural Network that we call Institutional Neural Network (INN).The main purpose of this paper is to bring attention to Artificial Teaching (AT) and to give a tentative answer showing a proof-of-concept implementation of Regulated Deep Learning (RDL). This paper introduces the former concept and provide $I^*$, a language previously used to model declaratively and extend Electronic Institutions, as a means to regulate the execution of Artificial Neural Networks and their interactions with Artificial Teachers (ATs)
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningSimilar Papers 제목 키워드 기반
Sticky information and price controls: Evidence from a natural experiment
We test the predictions of the sticky information model using a survey dataset by comparing shoppers accuracy in recalling the prices of regulated and comparable unregulated products. Because regulated product prices are…
A Missing Hallmark of Cancer: Dysregulation of Differentiation
Cancer cells possess a nearly universal set of characteristics termed the hallmarks of cancer, including replicative immortality and resisting cell death. Dysregulated differentiation is present in virtually all cancers …
PrognosisNonlinear Robust Periodic Output Regulation of Minimum Phase Systems
In linear systems theory it's a well known fact that a regulator given by the cascade of an oscillatory dynamics, driven by some regulated variables, and of a stabiliser stabilising the cascade of the plant and of the os…
BlockingScale-free linear protocol design for global regulated state synchronization of discrete-time double-integrator multi-agent systems subject to actuator saturation
This paper studies global regulated state synchronization of discrete-time double-integrator multi-agent systems subject to actuator saturation by utilizing localized information exchange. We propose a scale-free linear …
Transcriptional leakage versus noise: A simple mechanism of conversion between binary and graded response in autoregulated genes
We study the response of an autoregulated gene to a range of concentrations of signal molecules. We show that transcriptional leakage and noise due to translational bursting have the opposite effects. In a positively aut…