Close

Filter courses

Show courses Show filters
Close

Machine Learning for Semiconductor Quantum Devices

01 /Supervised Learning for quantum Dots 02 /Charge Stability Diagrams 03 /Classify CS Diagrams with Neural Networks 04 /Supervised Learning with Feedback 05 /Charge Tuning as a NN with Feedback 06 /Real-Life Experimental Applications 07 /Unsupervised Learning for Quantum Dots 08 /Analyse CS Diagrams with Clustering 09 /Analyse CS Diagrams with Unsupervised NNs 10 /Autoencoders in QD Experiments 11 /ML Fine Tuning of Quantum Dots 12 /Overhauser Field estimation 13 /Recap 14 /State of the Art Tuning

Charge Stability Diagrams

In this video, we review the concept of the charge stability diagram as a key type of data input for a significant portion of machine learning tuning tasks. We illustrate different types of charge transitions and the differences between single and double dot regimes. 

Prerequisite knowledge

Main takeaways

  •  
  • The charge stability diagram is a useful visual representation of quantum dot occupation as a function of control voltages.
  • We can directly observe charge transitions in the pattern of measured current.

Further thinking

Which of the following is the most accurate description of quantum point contact:

a. An electrode that controls occupation of a quantum dot
b. An electrode that defines a quantum dot
c. An electrode that helps us determine the occupation of a quantum dot
d. An electrode that adjusts all voltages in a quantum dot device

Solution

Further reading

A nice introduction to supervised learning with neural networks: https://ml-lectures.org/docs/supervised_learning_w_NNs/ml_supervised_w_NNs.html

Online book for Neural Networks and Deep Learning: http://neuralnetworksanddeeplearning.com/

Experimental paper that inspired the classification exercise we performed in this course: https://journals.aps.org/prapplied/abstract/10.1103/PhysRevApplied.13.054005 (Arxiv: https://arxiv.org/abs/1911.10709)