Electronic Resource
Variational Quantum Splines: Moving Beyond Linearity for Quantum Activation Functions
| العنوان: | Variational Quantum Splines: Moving Beyond Linearity for Quantum Activation Functions |
|---|---|
| المؤلفون: | Inajetovic, Matteo Antonio, thesis supervisor: Sartori, Claudio |
| بيانات النشر: | Alma Mater Studiorum - Università di Bologna Alma Mater Studiorum - Università di Bologna, 2022-07-20 |
| نوع الوثيقة: | Electronic Resource |
| مستخلص: | Activation functions within neural networks play a crucial role in Deep Learning since they allow to learn complex and non-trivial patterns in the data. However, the ability to approximate non-linear functions is a significant limitation when implementing neural networks in a quantum computer to solve typical machine learning tasks. The main burden lies in the unitarity constraint of quantum operators, which forbids non-linearity and poses a considerable obstacle to developing such non-linear functions in a quantum setting. Nevertheless, several attempts have been made to tackle the realization of the quantum activation function in the literature. Recently, the idea of the QSplines has been proposed to approximate a non-linear activation function by implementing the quantum version of the spline functions. Yet, QSplines suffers from various drawbacks. Firstly, the final function estimation requires a post-processing step; thus, the value of the activation function is not available directly as a quantum state. Secondly, QSplines need many error-corrected qubits and a very long quantum circuits to be executed. These constraints do not allow the adoption of the QSplines on near-term quantum devices and limit their generalization capabilities. This thesis aims to overcome these limitations by leveraging hybrid quantum-classical computation. In particular, a few different methods for Variational Quantum Splines are proposed and implemented, to pave the way for the development of complete quantum activation functions and unlock the full potential of quantum neural networks in the field of quantum machine learning. |
| مصطلحات الفهرس: | quantum computing,quantum variational algorithm,artificial intelligence,machine learning,QSplines,VQSplines,Activation Functions,VQLS,pennylane,quantum machine learning, PeerReviewed, info:eu-repo/semantics/masterThesis |
| URL: | |
| الاتاحة: | Open access content. Open access content Free to read |
| ملاحظة: | Free to read English |
| Other Numbers: | ITUDB oai:amslaurea.cib.unibo.it:26414 Inajetovic, Matteo Antonio (2022) Variational Quantum Splines: Moving Beyond Linearity for Quantum Activation Functions. [Laurea magistrale], Università di Bologna, Corso di Studio in Artificial intelligence [LM-DM270] <http://amslaurea.unibo.it/view/cds/CDS9063/> 1341400635 |
| المصدر المساهم: | UNIVERSITA DI BOLOGNA From OAIster®, provided by the OCLC Cooperative. |
| رقم الانضمام: | edsoai.on1341400635 |
| قاعدة البيانات: | OAIster |
| الوصف غير متاح. |