ETAI 2021 : Emerging Topics in Artificial Intelligence
Call For Papers
The ETAI conference provides a forum for a highly interdisciplinary community combining artificial intelligence with photonics, microscopy, active matter, biomedicine, and brain connectivity. Importantly, this conference includes topics outside the core expertise of optics and photonics. Photonics and machine learning have become decisively interdisciplinary, and we expect additional synergy and inspiration through this open-minded approach.
ETAI actively engages with industry to foster commercialization and provides networking opportunities for young and established researchers. By bringing experts from different fields and backgrounds together, ETAI provides new fundamental insights and identifies technological applications as well as commercialization opportunities.
The topics covered in ETAI include but are not limited to:
data acquisition and analysis through photonic subsystems, e.g., time series, images, video feature tracking, optical signal processing
simulation and design of photonic components and circuits
adaptive control of experimental setups through more robust and resilient feedback cycles
enhanced computational microscopy using artificial intelligence
alternative computing concepts such as neural networks and Ising machines to overcome the end of Moore and Dennard scaling
fundamental aspects of photonic non-digital computing
integrated photonics and nonlinear optical components for next generation computing
enhanced precision medicine, e.g., virtual tissue staining, early diagnosis, and personalized treatments
artificial intelligence for analysis of brain connectivity
biomimetic and neuromorphic computational architectures
embodied intelligence in nature and technology
evolution of adaptive behaviors in biological systems
engineering collective behaviors in robotic swarms
human brain haptic device interfaces
physical insight and interpretability of artificial intelligence models
limitations and criticism of the use of artificial intelligence.
The keynote and invited presentations will provide an exciting and broad view of this interdisciplinary research effort.
A flyer in PDF format is available at:
The ETAI conference will provide awards and prizes for the best oral presentation and the best poster presentation.
A panel discussion is being planned for the 2021 conference and will cover topics such as AI in photonics, AI in neurosciences, the future of AI, job opportunities for young researchers, and industry perspectives.
Abstracts are solicited on (but not restricted to) the following areas:
Artificial intelligence for photonics
optical system design using machine learning
machine learning-based solutions to inverse problems in optics
spectroscopy enhancement using machine learning.
Artificial intelligence for microscopy
data-driven optical reconstruction methods
digital video microscopy
generation of training datasets.
Artificial intelligence for optical trapping
optical trap calibration
Artificial intelligence for soft and active matter
data acquisition using machine learning
data analysis using machine learning
de-noising using machine learning
reinforcement learning in physical systems
dynamics of complex systems
navigation and search strategies.
Artificial intelligence for biomedicine
machine learning-enhanced optical imaging and sensing
virtual tissue staining
artificial intelligence as a tool to enhance decision-making in personalized medicine and drug screening
multiple-sources data structuring and combination in complex biomedical decision-making
legal and ethical aspects of the use of artificial intelligence as a tool for decision-making in medicine.
next generation materials for optical nonlinearity
integration of ultra-parallel photonic architectures
beyond 2D substrates
physical substrates for machine learning applications.
Optical neural networks
learning in optical systems
applications for optical neural networks
scalability of optical neural networks.
elaboration of sensorial inputs
Biological models for artificial intelligence
physical foundations of biological intelligence
translation of biological models to artificial intelligence
collective motion in biological populations.
Machine learning to study the brain
machine learning methods for image segmentation
supervised and unsupervised models
multi-voxel pattern analysis
predictive modelling approaches.
Artificial Intelligence for brain connectivity
measurement of brain activity and anatomy in humans and animals
structural and functional connectomics
graph theoretical tools
clusters and subnetwork extraction
dimensionality reduction techniques to identify brain networks.
detection of brain activity
feedback control through brain waves.
Limitations of artificial intelligence
the “black-box problem” of machine learning
interpretability, explainability and uncertainty quantification of machine-learning models
generalization power of machine-learning models
development of objective benchmarks.