SSIST by-talk Day 2

Keynote Talks

Yann Lecun and Harry Shum depict a grand road map of AI.

Speaking speed of Lecun is 3x faster than normal people. Fail to take and understand most part of his talk. The talk focused on CNN related project.

Keywords:

• Mask R-CNN instance segmentation
• ConvSeq2Seq for translation
• FAIR
• Memory network
• Stacked-augmented
• Neural turing network
• Differentiable memory

Harry Shum’s talk use XiaoIce as the example to depict the AI’s feature and MSRA’s work.

Computer Vision Topic

Some application in computer vision. There is no impressive talk.

Keywords:

• Pre-train use ImageNet
• Fine-tuning
• Gabor filter band
• FC layer
• Alex net

Security Topic

Dawn Song is the distinguished scientist in Secure deep learning. List many aspects that hackers can use in deep learning model and application. Deep learning’s security should start to be considered.

Other three’s talk isn’t suitable for me. Very boring.

Optimization Topic

Mathematics + English + BriefTalk = Though I know the word he talk, can’t understand any of them.

Conclusion

• Math related topic need a detailed preview !!!
• Most irrelevant application talking has nothing to do with you…
• Stay in RUJIA by myself….

Conference notes from SSIST 2017 Day 2.