{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hardware-for-machine-learning-challenges-and","title":"Hardware for Machine Learning: Challenges and Opportunities","arxiv_id":"1612.07625","date":"2016-12-22","proceeding":null,"authors":["Vivienne Sze","Yu-Hsin Chen","Joel Emer","Amr Suleiman","Zhengdong Zhang"],"abstract":"Machine learning plays a critical role in extracting meaningful information\nout of the zetabytes of sensor data collected every day. For some applications,\nthe goal is to analyze and understand the data to identify trends (e.g.,\nsurveillance, portable/wearable electronics); in other applications, the goal\nis to take immediate action based the data (e.g., robotics/drones, self-driving\ncars, smart Internet of Things). For many of these applications, local embedded\nprocessing near the sensor is preferred over the cloud due to privacy or\nlatency concerns, or limitations in the communication bandwidth. However, at\nthe sensor there are often stringent constraints on energy consumption and cost\nin addition to throughput and accuracy requirements. Furthermore, flexibility\nis often required such that the processing can be adapted for different\napplications or environments (e.g., update the weights and model in the\nclassifier). In many applications, machine learning often involves transforming\nthe input data into a higher dimensional space, which, along with programmable\nweights, increases data movement and consequently energy consumption. In this\npaper, we will discuss how these challenges can be addressed at various levels\nof hardware design ranging from architecture, hardware-friendly algorithms,\nmixed-signal circuits, and advanced technologies (including memories and\nsensors).","url_abs":"http://arxiv.org/abs/1612.07625v5","url_pdf":"http://arxiv.org/pdf/1612.07625v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hardware-for-machine-learning-challenges-and","repo_url":"https://github.com/michellbrito/CSCE_614_Term_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"self-driving-cars","task_name":"Self-Driving Cars"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}