The top Amazon Science articles of 2021

{"value":"\n\nThese are images from some of the most engaging stories published on Amazon Science in 2021.\n\n#### 1. An Amazon quantum computing scientist wins the first-ever quantum chess tournament\n\n[](https://www.amazon.science/latest-news/the-quantum-gambit)\n\nAleksander Kubica, research scientist with the AWS quantum computing team\n\nCREDIT: PERIMETER INSTITUTE FOR THEORETICAL PHYSICS\n\nNot only did Aleksander Kubica, a research scientist with the AWS quantum computing team, win the first-ever tournament, he did so having played quantum chess only once — the weekend before the event. [Learn about his strategy and watch video from two of his historic matches](https://www.amazon.science/latest-news/the-quantum-gambit).\n\n#### 2. A conversation with Michael I. Jordan, Michael Kearns, and Bernhard Schölkopf\n\n[](https://www.amazon.science/videos-webinars/neurips-luminaries-on-the-future-of-ai)\n\nLarry Hardesty, the Amazon Science blog editor, interviewed Amazon distinguished scientist Bernhard Schölkopf (top right) and Amazon Scholars Michael Kearns (bottom left) and Michael I. Jordan (bottom right).\n\nOn the cusp of the 2021 NeurIPS conference, the three Amazon-affiliated researchers — all of whom have given the conference’s major named lecture, the Posner lecture — talked about [the accelerating interesting in machine learning, its implications for both tech and AI research, and the path forward for AI](https://www.amazon.science/videos-webinars/neurips-luminaries-on-the-future-of-ai).\n\n#### 3. Graceful AI\n\n[](https://www.amazon.science/latest-news/graceful-ai)\n\nStefano Soatto, vice president of applied science for AWS AI.\n\nCREDIT: TODD CHENE\n\nStefano Soatto, vice president of applied science for AWS AI, writes, \"As machine-learning-based decision systems improve rapidly, we are discovering that it is no longer enough for them to perform well on their own. They should also behave nicely toward their predecessors. When we replace an old trained classifier with a new one, [we should expect a smooth transition and a peaceful transfer of decision powers.](https://www.amazon.science/latest-news/graceful-ai)\"\n\n#### 4. A look at the science that powers Amazon's advanced robot arms\n\n[](https://www.amazon.science/latest-news/amazon-robotics-see-robin-robot-arms-in-action)\n\nRobin must calculate how to identify, move, and sort parcels that may rest atop one another as they are presented via a conveyor.\n\nCREDIT F4D STUDIO\n\nRobin, one of the most complex stationary robot arm systems Amazon has ever built, brings many core technologies to new levels and acts as a glimpse into the possibilities of combining vision, package manipulation and machine learning. [Learn what separates them from more traditional robot arms — and watch them in action](https://www.amazon.science/latest-news/amazon-robotics-see-robin-robot-arms-in-action).\n\n#### 5. Why now is a 'particularly good time' to explore careers in robotics\n\n[](https://www.amazon.science/working-at-amazon/amazon-robotics-ai-leaders-believe-now-is-a-particularly-good-time-to-explore-careers-in-robotics)\n\nSiddhartha Srinivasa, left, director of Amazon Robotics AI, and Nia Jetter, Amazon Robotics AI senior principal technologist\n\nIn a video interview, Siddhartha Srinivasa, director of Amazon Robotics AI, and Nia Jetter, Amazon Robotics AI senior principal technologist, discuss inspiration, their roles at Amazon, and tips for pursuing a robotics career. [Watch their informative and illuminating discussion about careers in robotics.](https://www.amazon.science/working-at-amazon/amazon-robotics-ai-leaders-believe-now-is-a-particularly-good-time-to-explore-careers-in-robotics)\n\n#### 6. A computer vision system that can accurately predict body fat percentage\n\n[](https://www.amazon.science/latest-news/the-science-behind-the-amazon-halo-band-body-feature)\n\nWith Amazon Halo's Body feature, individuals can measure their own body fat percentage and track it through a personalized 3D model.\n\nA team of Amazon scientists [discusses the challenges in developing a system that can accurately estimate body fat percentage](https://www.amazon.science/latest-news/the-science-behind-the-amazon-halo-band-body-feature) and create personalized 3D avatars of users from smartphone photos. Learn how they utilized convolutional neural networks, and semi-supervised learning.\n\n#### 7. ARA recipient aims to unite the deep learning community\n\n[](https://www.amazon.science/research-awards/success-stories/michael-bronstein-aims-to-unite-the-deep-learning-community)\n\nMichael Bronstein, an Amazon Research Awards (ARA) recipient, is also the chair in Machine Learning and Pattern Recognition in the Department of Computing at Imperial College London\n\nDINO DIMOPOULOS\n\nMichael Bronstein, the chair in Machine Learning and Pattern Recognition in the Department of Computing at Imperial College London, is using pioneering machine learning [to push the boundaries of drug design, among other things — including unifing the machine learning “zoo”](https://www.amazon.science/research-awards/success-stories/michael-bronstein-aims-to-unite-the-deep-learning-community).\n\n#### 8. The science of operations planning under uncertainty\n\n[](https://www.amazon.science/latest-news/the-science-of-operations-planning-under-uncertainty)\n\nAn Amazon employee is seen making a delivery while an electric delivery van is parked behind him on a residential street in Los Angeles\n\nABOUT AMAZON\n\nWhen Amazon announced it would purchase 100,000 custom electric delivery vehicles as part of The Climate Pledge, a team of scientists within the Amazon Logistics (AMZL) Research organization took on the challenge of determining the best strategy for deploying them. Based on sophisticated models that simulate Amazon’s shipments and external parameters like power availability in each city, [the team is developing a plan to gradually electrify Amazon’s entire fleet](https://www.amazon.science/latest-news/the-science-of-operations-planning-under-uncertainty).\n\n#### 9， How machine learning is helping Amazon improve the grocery shopping experience\n\n[](https://www.amazon.science/latest-news/how-amazon-fresh-is-leveraging-scientific-innovation-to-meet-increased-consumer-demand)\n\nFrom forecasting to selection, Amazon Fresh scientists are developing machine learning models that seek to enhance the grocery shopping experience.\n\nFrom forecasting to selection, Amazon Fresh scientists are working through (often open) research challenges to develop machine learning models that seek to enhance the grocery shopping experience. [Learn how Amazon Fresh is leveraging scientific innovation to meet increased consumer demand.](https://www.amazon.science/latest-news/how-amazon-fresh-is-leveraging-scientific-innovation-to-meet-increased-consumer-demand)\n\n#### 10. Creating sustainable, data-driven buildings\n\n[](https://www.amazon.science/latest-news/creating-sustainable-data-driven-buildings)\n\nThe path to improving building energy efficiency can be paved with the framework of sense, act, and scale say Bharathan Balaji and Rob Aldrich\n\nBharathan Balaji , an Amazon senior research scientist, and Rob Aldrich, senior sustainability strategist, [write about what must happen to meet the United Nations Global Status Report goal of making buildings at least 30% more energy efficient](https://www.amazon.science/latest-news/creating-sustainable-data-driven-buildings) in order to achieve Paris Agreement goals.\n\nABOUT THE AUTHOR\n\n#### Staff writer","render":"<p><img src=\"https://dev-media.amazoncloud.cn/ab6a7bbf202f4cc39b3c2d2087f9e619_image.png\" alt=\"image.png\" /></p>\n<p>These are images from some of the most engaging stories published on Amazon Science in 2021.</p>\n<h4><a id=\"1_An_Amazon_quantum_computing_scientist_wins_the_firstever_quantum_chess_tournament_4\"></a>1. An Amazon quantum computing scientist wins the first-ever quantum chess tournament</h4>\n<p><a href=\"https://www.amazon.science/latest-news/the-quantum-gambit\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/ed385538832b41e5a0ac78be9e322193_image.png\" alt=\"image.png\" /></a></p>\n<p>Aleksander Kubica, research scientist with the AWS quantum computing team</p>\n<p>CREDIT: PERIMETER INSTITUTE FOR THEORETICAL PHYSICS</p>\n<p>Not only did Aleksander Kubica, a research scientist with the AWS quantum computing team, win the first-ever tournament, he did so having played quantum chess only once — the weekend before the event. <a href=\"https://www.amazon.science/latest-news/the-quantum-gambit\" target=\"_blank\">Learn about his strategy and watch video from two of his historic matches</a>.</p>\n<h4><a id=\"2_A_conversation_with_Michael_I_Jordan_Michael_Kearns_and_Bernhard_Schlkopf_14\"></a>2. A conversation with Michael I. Jordan, Michael Kearns, and Bernhard Schölkopf</h4>\n<p><a href=\"https://www.amazon.science/videos-webinars/neurips-luminaries-on-the-future-of-ai\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/4366c21e913141f09dfea35bcd2fb55c_image.png\" alt=\"image.png\" /></a></p>\n<p>Larry Hardesty, the Amazon Science blog editor, interviewed Amazon distinguished scientist Bernhard Schölkopf (top right) and Amazon Scholars Michael Kearns (bottom left) and Michael I. Jordan (bottom right).</p>\n<p>On the cusp of the 2021 NeurIPS conference, the three Amazon-affiliated researchers — all of whom have given the conference’s major named lecture, the Posner lecture — talked about <a href=\"https://www.amazon.science/videos-webinars/neurips-luminaries-on-the-future-of-ai\" target=\"_blank\">the accelerating interesting in machine learning, its implications for both tech and AI research, and the path forward for AI</a>.</p>\n<h4><a id=\"3_Graceful_AI_22\"></a>3. Graceful AI</h4>\n<p><a href=\"https://www.amazon.science/latest-news/graceful-ai\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/3a96d74c4dd44586bf2999a4d738c059_image.png\" alt=\"image.png\" /></a></p>\n<p>Stefano Soatto, vice president of applied science for AWS AI.</p>\n<p>CREDIT: TODD CHENE</p>\n<p>Stefano Soatto, vice president of applied science for AWS AI, writes, “As machine-learning-based decision systems improve rapidly, we are discovering that it is no longer enough for them to perform well on their own. They should also behave nicely toward their predecessors. When we replace an old trained classifier with a new one, <a href=\"https://www.amazon.science/latest-news/graceful-ai\" target=\"_blank\">we should expect a smooth transition and a peaceful transfer of decision powers.</a>”</p>\n<h4><a id=\"4_A_look_at_the_science_that_powers_Amazons_advanced_robot_arms_32\"></a>4. A look at the science that powers Amazon’s advanced robot arms</h4>\n<p><a href=\"https://www.amazon.science/latest-news/amazon-robotics-see-robin-robot-arms-in-action\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/2bd93503bf0a4054b209b46a4b9f5166_image.png\" alt=\"image.png\" /></a></p>\n<p>Robin must calculate how to identify, move, and sort parcels that may rest atop one another as they are presented via a conveyor.</p>\n<p>CREDIT F4D STUDIO</p>\n<p>Robin, one of the most complex stationary robot arm systems Amazon has ever built, brings many core technologies to new levels and acts as a glimpse into the possibilities of combining vision, package manipulation and machine learning. <a href=\"https://www.amazon.science/latest-news/amazon-robotics-see-robin-robot-arms-in-action\" target=\"_blank\">Learn what separates them from more traditional robot arms — and watch them in action</a>.</p>\n<h4><a id=\"5_Why_now_is_a_particularly_good_time_to_explore_careers_in_robotics_42\"></a>5. Why now is a ‘particularly good time’ to explore careers in robotics</h4>\n<p><a href=\"https://www.amazon.science/working-at-amazon/amazon-robotics-ai-leaders-believe-now-is-a-particularly-good-time-to-explore-careers-in-robotics\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/5f7fea35b23f47e79dcd247483574ac4_image.png\" alt=\"image.png\" /></a></p>\n<p>Siddhartha Srinivasa, left, director of Amazon Robotics AI, and Nia Jetter, Amazon Robotics AI senior principal technologist</p>\n<p>In a video interview, Siddhartha Srinivasa, director of Amazon Robotics AI, and Nia Jetter, Amazon Robotics AI senior principal technologist, discuss inspiration, their roles at Amazon, and tips for pursuing a robotics career. <a href=\"https://www.amazon.science/working-at-amazon/amazon-robotics-ai-leaders-believe-now-is-a-particularly-good-time-to-explore-careers-in-robotics\" target=\"_blank\">Watch their informative and illuminating discussion about careers in robotics.</a></p>\n<h4><a id=\"6_A_computer_vision_system_that_can_accurately_predict_body_fat_percentage_50\"></a>6. A computer vision system that can accurately predict body fat percentage</h4>\n<p><a href=\"https://www.amazon.science/latest-news/the-science-behind-the-amazon-halo-band-body-feature\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/5b526033957142149967fbd18e36a89e_image.png\" alt=\"image.png\" /></a></p>\n<p>With Amazon Halo’s Body feature, individuals can measure their own body fat percentage and track it through a personalized 3D model.</p>\n<p>A team of Amazon scientists <a href=\"https://www.amazon.science/latest-news/the-science-behind-the-amazon-halo-band-body-feature\" target=\"_blank\">discusses the challenges in developing a system that can accurately estimate body fat percentage</a> and create personalized 3D avatars of users from smartphone photos. Learn how they utilized convolutional neural networks, and semi-supervised learning.</p>\n<h4><a id=\"7_ARA_recipient_aims_to_unite_the_deep_learning_community_58\"></a>7. ARA recipient aims to unite the deep learning community</h4>\n<p><a href=\"https://www.amazon.science/research-awards/success-stories/michael-bronstein-aims-to-unite-the-deep-learning-community\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/e592498177b344edbd8c451f61d2ec7a_image.png\" alt=\"image.png\" /></a></p>\n<p>Michael Bronstein, an Amazon Research Awards (ARA) recipient, is also the chair in Machine Learning and Pattern Recognition in the Department of Computing at Imperial College London</p>\n<p>DINO DIMOPOULOS</p>\n<p>Michael Bronstein, the chair in Machine Learning and Pattern Recognition in the Department of Computing at Imperial College London, is using pioneering machine learning <a href=\"https://www.amazon.science/research-awards/success-stories/michael-bronstein-aims-to-unite-the-deep-learning-community\" target=\"_blank\">to push the boundaries of drug design, among other things — including unifing the machine learning “zoo”</a>.</p>\n<h4><a id=\"8_The_science_of_operations_planning_under_uncertainty_68\"></a>8. The science of operations planning under uncertainty</h4>\n<p><a href=\"https://www.amazon.science/latest-news/the-science-of-operations-planning-under-uncertainty\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/39c9b81fadda4609a6edaf2e311f470d_image.png\" alt=\"image.png\" /></a></p>\n<p>An Amazon employee is seen making a delivery while an electric delivery van is parked behind him on a residential street in Los Angeles</p>\n<p>ABOUT AMAZON</p>\n<p>When Amazon announced it would purchase 100,000 custom electric delivery vehicles as part of The Climate Pledge, a team of scientists within the Amazon Logistics (AMZL) Research organization took on the challenge of determining the best strategy for deploying them. Based on sophisticated models that simulate Amazon’s shipments and external parameters like power availability in each city, <a href=\"https://www.amazon.science/latest-news/the-science-of-operations-planning-under-uncertainty\" target=\"_blank\">the team is developing a plan to gradually electrify Amazon’s entire fleet</a>.</p>\n<h4><a id=\"9_How_machine_learning_is_helping_Amazon_improve_the_grocery_shopping_experience_78\"></a>9， How machine learning is helping Amazon improve the grocery shopping experience</h4>\n<p><a href=\"https://www.amazon.science/latest-news/how-amazon-fresh-is-leveraging-scientific-innovation-to-meet-increased-consumer-demand\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/8bbcc01bdd314f8496cb575978221bce_image.png\" alt=\"image.png\" /></a></p>\n<p>From forecasting to selection, Amazon Fresh scientists are developing machine learning models that seek to enhance the grocery shopping experience.</p>\n<p>From forecasting to selection, Amazon Fresh scientists are working through (often open) research challenges to develop machine learning models that seek to enhance the grocery shopping experience. <a href=\"https://www.amazon.science/latest-news/how-amazon-fresh-is-leveraging-scientific-innovation-to-meet-increased-consumer-demand\" target=\"_blank\">Learn how Amazon Fresh is leveraging scientific innovation to meet increased consumer demand.</a></p>\n<h4><a id=\"10_Creating_sustainable_datadriven_buildings_86\"></a>10. Creating sustainable, data-driven buildings</h4>\n<p><a href=\"https://www.amazon.science/latest-news/creating-sustainable-data-driven-buildings\" target=\"_blank\"><img src=\"https://dev-media.amazoncloud.cn/c02f0561e833463daf7c72737d2f2449_%E4%B8%8B%E8%BD%BD.gif\" alt=\"下载.gif\" /></a></p>\n<p>The path to improving building energy efficiency can be paved with the framework of sense, act, and scale say Bharathan Balaji and Rob Aldrich</p>\n<p>Bharathan Balaji , an Amazon senior research scientist, and Rob Aldrich, senior sustainability strategist, <a href=\"https://www.amazon.science/latest-news/creating-sustainable-data-driven-buildings\" target=\"_blank\">write about what must happen to meet the United Nations Global Status Report goal of making buildings at least 30% more energy efficient</a> in order to achieve Paris Agreement goals.</p>\n<p>ABOUT THE AUTHOR</p>\n<h4><a id=\"Staff_writer_96\"></a>Staff writer</h4>\n"}