从10月29日到现在,3分钟学术视频演讲大赛作品展示及预热活动——礼品助力投票已过大半,感谢各位读者的参与,也恭喜此前已展示作品的参赛者获得了大家为他们“精心”挑选的礼品。
相信各位在“上半程”里已经看到了不少精彩的作品。在接下来的“下半程”,还会有3个批次共9个作品展示(包括今天展示的3个作品),这些作品是否会让您拍案称赞?我们期待您的反馈。
Non-line-of-sight imaging over 1.43km
参赛者:
刘健江-中国科学技术大学
Perovskite light-emitting diodes based on spontaneously formed submicrometre-scale structures
Learning Credit Assignment
为了破解深度学习黑箱,建立神经网络决策与微观组分之间的桥梁,我们提出一种由稀疏度与均值方差刻画的随机连接权重模型,通过平均场方法训练得到系综水平上一组子网络,并在真实据集上获得了不弱于传统方法的表现。
Credit assignment problem (CAP) has long been an interesting topic connecting the macroscopic behaviors with microscopic interactions of components in deep neural networks. To solve this problem and reveal the mystery behind the black box of deep learning, we put forward a model with random weights characterized by a spike and slab distribution, which obtains comparable or even better performance than traditional models. An optimal random network ensemble can be achieved after training based on mean-field theory.
前4批展示作品的链接 (注:礼品助力投票时限已过,助TA挑选礼品二维码已经失效):
如果篇首注明了授权来源,任何转载需获得来源方的许可!如果篇首未特别注明出处,本文版权属于 X-MOL ( x-mol.com ), 未经许可,谢绝转载!