دانلود کتاب پردازش در حافظه برای هوش مصنوعی از مدارها تا سیستم ها

Artificial intelligence (AI) and machine learning (ML) technology enable computers to mimic the cognitive tasks believed to be what only humans can do, such as recognition, understanding, and reasoning. A deep ML model named AlexNet, which uses eight layers in total, won the famous large-scale image recognition competition called ImageNet by a significant margin over shallow ML models in 2012. Since then, deep learning (DL) revolution has been ignited and spread to many other domains such as speech recognition, natural language processing, virtual assistance, autonomous vehicle, and robotics.With significant successes in various domains, DL revolutionizes a wide range of industry sectors such as information technology, mobile communication, automotive, and manufacturing. However, as more industries adopt the new technology and more people use it daily, we face an ever-increasing demand for a new type of hardware for the workloads. Conventional hardware platforms such as CPU and GPU are not suitable for the new workloads. CPUs cannot cope with the tremendous amount of data transfers and computations required in the ML workloads, while GPUs consume large amounts of power with high operating costs.