Refine
Document Type
- Journal article (2)
Language
- English (2)
Has full text
- yes (2)
Is part of the Bibliography
- yes (2)
Institute
- Informatik (1)
- Life Sciences (1)
- Technik (1)
Analog integrated circuit sizing is notoriously difficult to automate due to its complexity and scale; thus, it continues to heavily rely on human expert knowledge. This work presents a machine learning-based design automation methodology comprising pre-defined building blocks such as current mirrors or differential pairs and pre-computed look-up tables for electrical characteristics of primitive devices. Modeling the behavior of primitive devices around the operating point with neural networks combines the speed of equation-based methods with the accuracy of simulation-based approaches and, thereby, brings quality of life improvements for analog circuit designers using the gm/Id method. Extending this procedural automation method for human design experts, we present a fully autonomous sizing approach. Related work shows that the convergence properties of conventional optimization approaches improve significantly when acting in the electrical domain instead of the geometrical domain. We, therefore, formulate the circuit sizing task as a sequential decision-making problem in the alternative electrical design space. Our automation approach is based entirely on reinforcement learning, whereby abstract agents learn efficient design space navigation through interaction and without expert guidance. These agents’ learning behavior and performance are evaluated on circuits of varying complexity and different technologies, showing both the feasibility and portability of the work presented here.
Cells can sense geometrical cues with sizes of several tens of micrometers in their vicinity. Recent in vitro studies show that cells can adapt their shape, align along specific directions, or regulate other cellular functions when grown on surfaces with curvatures larger than their size. Although possible mechanisms for such responses like the alignment along axial cues have been suggested, a detailed understanding of the involved cellular processes remains open. This work addresses this gap by systematically investigating mesenchymal cell and nucleus orientation responses using a low‐cost model surface platform, the CurvChip. Using an array of cylindrically curved topographies with radii of curvatures ranging from tens to hundreds of micrometers, the contact guidance response of cells and nuclei is quantified in dependence on substratum curvature and manipulation of cytoskeletal components. Results suggest a desired perceived curvature for the investigated cells, and a very sensitive and robust curvature perception mechanism, as the effect of pharmacological manipulation of cytoskeletal components is relatively small. Furthermore, a comparison with previously published work strengthens the hypothesis of an involvement of the nucleus in the cell response to three‐dimensional (3D) curvatures.
