Objective
Driven by the AI boom, technologies such as robotics, virtual reality, and self-driving have begun to emerge, leading to an ever-increasing demand for high-efficiency, data-intensive computing. Inspired by the brain, post-von-Neumann neuromorphic computing was proposed. Mapping the biological neural networks to implement neuromorphic computing requires both algorithm and hardware designs. Although the algorithm approach is being widely exploited, neuromorphic hardware is still in its early stages of development, requiring continual advancements in the underlying materials, devices, and circuits. This course covers the most up-to-date research in the field of neuromorphic hardware. The course will begin with an introduction to neuromorphic computing, followed by discussions on neuromorphic hardware development, in which the students will study the materials, devices, and circuits exploited to enable neuromorphic hardware. In addition to lectures, the course includes lab case study sessions where students can have experience with neuromorphic hardware fabrication.
在人工智能熱潮的推動下，機器人、虛擬現實和自動駕駛等技術開始湧現，對高效、數據密集型的計算提出了不斷增長的需求。受大腦計算模型的啟發，後馮諾依曼的類腦計算方式被提出。映射生物神經網絡以實現類腦計算需要算法和硬件的設計。儘管類腦計算算法被廣泛使用，類腦計算的硬件開發仍處於早期階段，而它的發展依賴於其底層材料、器件和電路的不斷發展。本課程將討論類腦計算硬件設計的最新研究。課程將首先介紹類腦計算的概念，然後詳細討論類腦計算的硬件設計。學生將學習類腦計算硬件設計實現的材料、設備和電路。除了課堂授課，課程還設計了實驗室展示環節，學生可以在實驗室中參觀類腦計算的硬件製備。
Syllabus
Introduction to neuromorphic computing; Review on semiconductors, semiconductor devices and circuits; von Neumann architecture; Hardware implementations of artificial synapses and neurons; Device and circuit design and fabrication for neuromorphic hardware.
Learning Outcome
Upon successful completion of the course, students will be able to
- Be familiar with the von Neumann and non-von Neumann hardware architectures
- Gain the key fundamental knowledge of semiconductors, semiconductor devices and circuits to implement computation
- Apply the fundamental semiconductor knowledge to the design and implementation of the biological synapses and neurons and the neuromorphic hardware
- Well understand neuromorphic hardware development at device and circuit levels
