Quantum machine learning (QML) aims to address some fundamental limitations of classical ML, like computational complexity issues, etc.

If you want to study QML, here are five recommended resources to start your journey with:

#quantumcomputing #qiqc #deeplearning #ml #qml

1️⃣ IBM Qiskit Global Summer School 2021 by @qiskit (https://qiskit.org/learn/summer-school/quantum-computing-and-quantum-learning-2021)

• Gives an overview of classical ML before tackling quantum concepts

• Provides a good set of guided exercises

2️⃣ @PennyLaneAI QML resources (https://pennylane.ai/qml/) by @XanaduAI

• Focuses more on SOTA QML algorithms on NISQ hardware

• Caters towards more advanced learners

• Lists a comprehensive set of demo notebooks for the algorithms

3️⃣ QML MOOC by Peter Wittek (https://www.youtube.com/playlist?list=PLmRxgFnCIhaMgvot-Xuym_hn69lmzIokg)

• Discusses essential quantum computing concepts first before focusing on a couple of QML algorithms

• Works well in tandem with both the previous resources

4️⃣ Stanford CS229: Machine Learning Course 2019 by @StanfordEng (https://www.youtube.com/watch?v=KzH1ovd4Ots&list=PLoROMvodv4rNH7qL6-efu_q2_bPuy0adh)

• Uses a bottom-up approach - starts with math fundamentals like linear algebra, statistics, etc. before tackling ML/DL algorithms

• Good supplement for top-down approaches

5️⃣ Practical Deep Learning for Coders 2022 (https://www.youtube.com/watch?v=8SF_h3xF3cE&list=PLfYUBJiXbdtSvpQjSnJJ_PmDQB_VyT5iU) by @fastdotai

• Uses a top-down, hands-on approach to teach deep learning - you can have a working trained model by the end of the 1st lecture

• Useful if your use-case is classical algorithms on quantum data

Again, this list is not comprehensive - these are just the ones I use as my primary reference. Nothing beats implementing stuff after you read/watch a lecture about it.

#quantumcomputing #qiqc #deeplearning #ml #qml