• <tr id='kMujp3'><strong id='kMujp3'></strong><small id='kMujp3'></small><button id='kMujp3'></button><li id='kMujp3'><noscript id='kMujp3'><big id='kMujp3'></big><dt id='kMujp3'></dt></noscript></li></tr><ol id='kMujp3'><option id='kMujp3'><table id='kMujp3'><blockquote id='kMujp3'><tbody id='kMujp3'></tbody></blockquote></table></option></ol><u id='kMujp3'></u><kbd id='kMujp3'><kbd id='kMujp3'></kbd></kbd>

    <code id='kMujp3'><strong id='kMujp3'></strong></code>

    <fieldset id='kMujp3'></fieldset>
          <span id='kMujp3'></span>

              <ins id='kMujp3'></ins>
              <acronym id='kMujp3'><em id='kMujp3'></em><td id='kMujp3'><div id='kMujp3'></div></td></acronym><address id='kMujp3'><big id='kMujp3'><big id='kMujp3'></big><legend id='kMujp3'></legend></big></address>

              <i id='kMujp3'><div id='kMujp3'><ins id='kMujp3'></ins></div></i>
              <i id='kMujp3'></i>
            1. <dl id='kMujp3'></dl>
              1. <blockquote id='kMujp3'><q id='kMujp3'><noscript id='kMujp3'></noscript><dt id='kMujp3'></dt></q></blockquote><noframes id='kMujp3'><i id='kMujp3'></i>

                学术讲座

                您所在◥的位置: 首页? 首页栏目? 学术讲座

                学术讲座

                【湘江□高端论坛】Enabling Efficient Computer Architectural and System Support for Next-Generation Deep Learning Applications

              2. <tr id='kMujp3'><strong id='kMujp3'></strong><small id='kMujp3'></small><button id='kMujp3'></button><li id='kMujp3'><noscript id='kMujp3'><big id='kMujp3'></big><dt id='kMujp3'></dt></noscript></li></tr><ol id='kMujp3'><option id='kMujp3'><table id='kMujp3'><blockquote id='kMujp3'><tbody id='kMujp3'></tbody></blockquote></table></option></ol><u id='kMujp3'></u><kbd id='kMujp3'><kbd id='kMujp3'></kbd></kbd>

                  <code id='kMujp3'><strong id='kMujp3'></strong></code>

                  <fieldset id='kMujp3'></fieldset>
                        <span id='kMujp3'></span>

                            <ins id='kMujp3'></ins>
                                <acronym id='kMujp3'><em id='kMujp3'></em><td id='kMujp3'><div id='kMujp3'></div></td></acronym><address id='kMujp3'><big id='kMujp3'><big id='kMujp3'></big><legend id='kMujp3'></legend></big></address>

                                  <i id='kMujp3'><div id='kMujp3'><ins id='kMujp3'></ins></div></i>
                                  <i id='kMujp3'></i>
                                    • <dl id='kMujp3'></dl>
                                        <blockquote id='kMujp3'><q id='kMujp3'><noscript id='kMujp3'></noscript><dt id='kMujp3'></dt></q></blockquote><noframes id='kMujp3'><i id='kMujp3'></i>

                                        湘江≡高端论坛学术报告会预告:

                                        Enabling Efficient Computer Architectural and System Support for Next-Generation Deep Learning Applications


                                        湖南科技大学计算机科学∮与工程学院将于2022312日(周)举行主◢题为Enabling Efficient Computer Architectural and System Support for Next-Generation Deep Learning Applications”的学术报告会∩。敬请光临!


                                        报告题目:Enabling Efficient Computer Architectural and System Support for Next-Generation Deep Learning Applications

                                        报 告 人:长江学者  李涛 教授

                                        报告时间:2022312 日周 10:30

                                        报告地点:逸夫楼201会议室


                                        报告摘要:

                                        In recent years, the artificial intelligence (AI) techniques, represented by deep neural networks (DNN), have emerged as indispensable tools in many fields. Traditionally, due to its huge compute power and scalability, the cloud data center is often the best option for training and evaluating AI applications. With the increasing computing power and energy efficiency of mobile devices, there is a growing interest in performing AI applications on mobile platforms. As a result, we believe the next-generation AI applications are pervasive across all platforms, ranging from central cloud data center to edge-side wearable and mobile devices.

                                        However, we observe several gaps that challenge the pervasive AI applications. First, the large size of such newly developed AI networks poses both throughput and energy challenges to the underlying processing hardware, which hinders ubiquitous deployment for many promising AI applications. Second, the traditional statically trained AI model in cloud data center could not efficiently handle the dynamic data in the real in-situ environments, which leads to low inference accuracy. Lastly, the training of AI models still involves extensive human efforts to collect and label the large-scale dataset, which becomes impractical in big data era where raw data is largely un-labeled and uncategorized.

                                        In this talk, I will present architecture and system support which enables next generation AI applications to become high efficient and intelligent. I will first introduce Pervasive AI, a user satisfaction-aware deep learning inference framework, to provide the best user satisfaction when migrating AI-based applications from Cloud to all kinds of platforms. Next, I will describe In-situ AI, a novel-computing paradigm tailored to in-situ AI applications. Furthermore, to tackle the big data challenge and achieve real intelligent (support autonomous learning), I will introduce Unsupervised AI, an unsupervised GAN-based deep learning accelerator.