麻豆精品无码av,欧美1区2区,久久中文字幕乱码人妻,亚洲欧美另类少妇精品,在线看黄射,69pao高清,九九九久久久国产精品,子操大逼1234区,九九爱99热精品

8
點(diǎn)贊
0
評(píng)論
0
轉(zhuǎn)載
收藏

團(tuán)隊(duì)一篇論文被國(guó)際頂刊 IEEE TPAMI錄用

    2024年伊始,團(tuán)隊(duì)論文“Learning from Human Educational Wisdom: A Student-Centered Knowledge Distillation Method ”被人工智能領(lǐng)域國(guó)際頂刊IEEE Transactions on Pattern Analysis and Machine IntelligenceCCF A,IF=23.6)錄用,學(xué)生為第一作者,本人為通訊作者,主要通過(guò)知識(shí)蒸餾技術(shù)使得輕量級(jí)小模型在智能手機(jī)、攝像頭、機(jī)器人和無(wú)人車(chē)(機(jī))等資源受限的終端設(shè)備上具有云端大模型的性能。

    Abstract——Existing studies on knowledge distillation typically focus on teacher-centered methods, in which the teacher network is trained according to its own standards before transferring the learned knowledge to a student one. However, due to differences in network structure between the teacher and the student, the knowledge learned by the former may not be desired by the latter. Inspired by human educational wisdom, this paper proposes a Student-Centered Distillation (SCD) method that enables the teacher network to adjust its knowledge transfer according to the student network’s needs. We implemented SCD based on various human educational wisdom, e.g., the teacher network identified and learned the knowledge desired by the student network on the validation set, and then transferred it to the latter through the training set. To address the problems of current deficiency knowledge, hard sample learning and knowledge forgetting faced by a student network in the learning process, we introduce and improve Proportional-Integral-Derivative (PID) algorithms from automation fields to make them effective in identifying the current knowledge required by the student network. Furthermore, we propose a curriculum learning-based fuzzy strategy and apply it to the proposed PID control algorithm, such that the student network in SCD can actively pay attention to the learning of challenging samples after with certain knowledge. The overall performance of SCD is verified in multiple tasks by comparing it with state-of-the-art ones. Experimental results show that our student-centered distillation method outperforms existing teacher-centered ones.

    Keywords——Knowledge distillation, human educational wisdom, student-centered, fuzzy PID, curriculum learning 

 

聲明:本內(nèi)容系學(xué)者網(wǎng)用戶個(gè)人學(xué)術(shù)動(dòng)態(tài)分享,不代表平臺(tái)立場(chǎng)。

SCHOLAT.com 學(xué)者網(wǎng)
免責(zé)聲明 | 關(guān)于我們 | 聯(lián)系我們
聯(lián)系我們:
返回頂部
贵港市| 河源市| 永春县| 浮梁县| 泰顺县| 乌兰浩特市| 通海县| 台山市| 温州市| 和硕县| 乳山市| 庆阳市| 夏邑县| 高碑店市| 静海县| 云梦县| 南溪县| 唐山市| 琼海市| 长春市| 武鸣县| 闻喜县| 平远县| 太白县| 屯留县| 新丰县| 阿瓦提县| 城口县| 大城县| 南阳市| 四川省| 乌兰县| 石景山区| 北辰区| 孝义市| 呼伦贝尔市| 仁怀市| 台南县| 峨山| 晋城| 任丘市|