Search for: All records

Artificial intelligence (AI) provides versatile capabilities in applications such as image classification and voice recognition that are most useful in edge or mobile computing settings. Shrinking these sophisticated algorithms into small form factors with minimal computing resources and power budgets requires innovation at several layers of abstraction: software, algorithmic, architectural, circuit, and device-level innovations. However, improvements to system efficiency may impact robustness and vice-versa. Therefore, a co-design framework is often necessary to customize a system for its given application. A system that prioritizes efficiency might use circuit-level innovations that introduce process variations or signal noise into the system, which may use software-level redundancy in order to compensate. In this tutorial, we will first examine various methods of improving efficiency and robustness in edge AI and their tradeoffs at each level of abstraction.Then, we will outline co-design techniques for designing efficient and robust edge AI systems, using federated learning as a specific example to illustrate the effectiveness of co-design. 

The unprecedented success of artificial intelligence (AI) enriches machine learning (ML)-based applications. The availability of big data and compute-intensive algorithms empowers versatility and high accuracy in ML approaches. However, the data processing and innumerable computations burden conventional hardware systems with high power consumption and low performance. Breaking away from the traditional hardware design, non-conventional accelerators exploiting emerging technology have gained significant attention with a leap forward since the emerging devices enable processing-in-memory (PIM) designs of dramatic improvement in efficiency. This paper presents a summary of state-of-the-art PIM accelerators over a decade. The PIM accelerators have been implemented for diverse models and advanced algorithm techniques across diverse neural networks in language processing and image recognition to expedite inference and training. We will provide the implemented designs, methodologies, and results, following the development in the past years. The promising direction of the PIM accelerators, vertically stacking for More than Moore, is also discussed. 

Abstract HP1 proteins are essential for establishing and maintaining transcriptionally silent heterochromatin. They dimerize, forming a binding interface to recruit diverse chromatin-associated factors. Although HP1 proteins are known to rapidly evolve, the extent of variation required to achieve functional specialization is unknown. To investigate how changes in amino acid sequence impacts heterochromatin formation, we performed a targeted mutagenesis screen of theS. pombeHP1 homolog, Swi6. Substitutions within an auxiliary surface adjacent to the HP1 dimerization interface produce Swi6 variants with divergent maintenance properties. Remarkably, substitutions at a single amino acid position lead to the persistent gain or loss of epigenetic inheritance. These substitutions increase Swi6 chromatin occupancy in vivo and altered Swi6-protein interactions that reprogram H3K9me maintenance. We show how relatively minor changes in Swi6 amino acid composition in an auxiliary surface can lead to profound changes in epigenetic inheritance providing a redundant mechanism to evolve HP1-effector specificity.