In the past few years, Artificial Intelligence (AI) has been a subject of intense media hype. Machine learning, deep learning (DL), and AI come up in countless articles, often outside of technology-minded publications. As the AI hype keeps growing, it is important to be able to recognize the signal in the noise, to tell apart world-changing developments from what are merely over-hyped press releases. This paper tries to explain how deep learning is working and how GPU (Graphic Processing Unite) can make it a reality. Finally, in-memory computing (IMC) for DL is introduced to point out future high performance and low power DL hardware development direction.
Phase change material (PCM)-based memory cells have shown promise as an enabler for low power, high density memory. There is a current need to develop and improve patterning strategies to attain smaller device dimensions. In this work, two methods of patterning of PCM device structures was achieved using directed self-assembly (DSA) patterning: the formation of a high aspect ratio pore designed for atomic layer deposition (ALD) of etch damage-free PCM, and pillar formation by image reversal and plasma etch transfer into a PCM film. We show significant CD reduction (180 nm to 20 nm) of a lithographically defined hole by plasma etch shrink, DSA spin-coat and subsequent high selectivity pattern transfer. We then demonstrate structural fabrication of both DSA-defined SiN pores with ALD PCM and DSA-defined PCM pillars. Challenges to both pore and pillar fabrication are discussed.