<em id="xltbt"><nobr id="xltbt"><meter id="xltbt"></meter></nobr></em>
      <form id="xltbt"><form id="xltbt"><nobr id="xltbt"></nobr></form></form>

          <sub id="xltbt"><listing id="xltbt"><menuitem id="xltbt"></menuitem></listing></sub>

            <address id="xltbt"></address>
            <address id="xltbt"><listing id="xltbt"></listing></address>

            首 頁機構概況機構設置科研人才隊伍合作交流研究生教育博士后圖書館創新文化黨群園地院重點實驗室彭桓武中心信息公開
              學術活動
              您現在的位置:首頁 > 學術活動 > 專題學術報告/Seminar
            (Seminar) Bayesian tensor network: towards efficient and interpretable probabilistic machine learning
            2020-11-02  【 】【打印】【關閉

            CAS Key Laboratory of Theoretical Physics

            Institute of Theoretical Physics

            Chinese Academy of Sciences

             Seminar

            Title

            題目

            Bayesian tensor network: towards efficient and interpretable probabilistic machine learning

            Speaker

            報告人

            冉仕舉

            Affiliation

            所在單位

            首都師范大學

            Date

            日期

            2020年11月2日10:00-11:00

            Venue

            地點

            ITP South Building 6420

            Contact Person

            所內聯系人

            張潘

            Abstract

            摘要

            Developing novel machine learning models with both high interpretability and efficiency is an important but extremely challenging issue. In this work, Bayesian tensor network (BTN) is proposed by combining Bayesian statistics with tensor network (TN), which captures the conditional probabilities of exponentially many events efficiently with polynomial complexity and meanwhile retraining high interpretability as a probabilistic model. BTN is tested on classifying images of hand-written digits and fashion articles, where the classification tasks are mapped to the problems of capturing the conditional probabilities in an exponentially large sample space. Impressive performance using simple loop-free structures are demonstrated with insignificant over-fitting. Furthermore, BTN can be used to as a module to construct novel end-to-end models by hybridizing with neural networks.
            IE6.0瀏覽器,1024X768分辨率 版權所有 ? 中國科學院理論物理研究所
            地址:北京市海淀區中關村東路55號 郵政編碼:100190
            京ICP備05002865號】 京公網安備1101080094號
            欧美另类杂交a,特黄作爱又粗又硬又大片,她高耸的双乳诱人的粉色奶头

                <em id="xltbt"><nobr id="xltbt"><meter id="xltbt"></meter></nobr></em>
                <form id="xltbt"><form id="xltbt"><nobr id="xltbt"></nobr></form></form>

                    <sub id="xltbt"><listing id="xltbt"><menuitem id="xltbt"></menuitem></listing></sub>

                      <address id="xltbt"></address>
                      <address id="xltbt"><listing id="xltbt"></listing></address>