Lecture by Andrew Trask in January 2020, part of the MIT Deep Learning Lecture Series.
Website:
Slides:
Playlist:
LINKS:
Andrew Twitter:
OpenMined:
Grokking Deep Learning (book):
OUTLINE:
0:00 – Introduction
0:54 – Privacy preserving AI talk overview
1:28 – Key question: Is it possible to answer questions using data we cannot see?
5:56 – Tool 1: remote execution
8:44 – Tool 2: search and example data
11:35 – Tool 3: differential privacy
28:09 – Tool 4: secure multi-party computation
36:37 – Federated learning
39:55 – AI, privacy, and society
46:23 – Open data for science
50:35 – Single-use accountability
54:29 – End-to-end encrypted services
59:51 – Q&A: privacy of the diagnosis
1:02:49 – Q&A: removing bias from data when data is encrypted
1:03:40 – Q&A: regulation of privacy
1:04:27 – Q&A: OpenMined
1:06:16 – Q&A: encryption and nonlinear functions
1:07:53 – Q&A: path to adoption of privacy-preserving technology
1:11:44 – Q&A: recommendation systems
CONNECT:
– If you enjoyed this video, please subscribe to this channel.
– Twitter:
– LinkedIn:
– Facebook:
– Instagram:
Table of Contents
Images related to the topic ai technology for education
Privacy Preserving AI (Andrew Trask) | MIT Deep Learning Series
Search related to the topic Privacy Preserving AI (Andrew Trask) | MIT Deep Learning Series
#Privacy #Preserving #Andrew #Trask #MIT #Deep #Learning #Series
Privacy Preserving AI (Andrew Trask) | MIT Deep Learning Series
ai technology for education
You can see a lot of useful information here: See more here
You can see a lot of useful information here: See more here
33 comments
I really enjoyed this talk by Andrew. Here's the outline:
0:00 – Introduction
0:54 – Privacy preserving AI talk overview
1:28 – Key question: Is it possible to answer questions using data we cannot see?
5:56 – Tool 1: remote execution
8:44 – Tool 2: search and example data
11:35 – Tool 3: differential privacy
28:09 – Tool 4: secure multi-party computation
36:37 – Federated learning
39:55 – AI, privacy, and society
46:23 – Open data for science
50:35 – Single-use accountability
54:29 – End-to-end encrypted services
59:51 – Q&A: privacy of the diagnosis
1:02:49 – Q&A: removing bias from data when data is encrypted
1:03:40 – Q&A: regulation of privacy
1:04:27 – Q&A: OpenMined
1:06:16 – Q&A: encryption and nonlinear functions
1:07:53 – Q&A: path to adoption of privacy-preserving technology
1:11:44 – Q&A: recommendation systems
He is talking so fast. Or is the video accelerated by default?
Cool to see Nick Mullen has gotten into computer science
What a fantastic talk, enjoyed every minute of it. He also wants the talk himself, which is quite interesting.
28:00, the data is safe, but the model is put at risk/do a join/computation across multiple data owners.
Can't differential privacy handle these? Do DP has these two Cons?
I love this
Excellent talk! Really enjoyed it.
popularizing spyware ? Remember up is down, left is right, and the party will tell you what you need to know. Let's install more spyware so that people will have better privacy.
The most complex thing here is to not look at the line integral on the blackboard:))
heeey im getting 4 mid video ads in one go now ;( (great intro to ppML)
Very good talk. But I dont like the way he continues to raise his hand and ask if there anybody knows that or if there anybody knows this. What a embarrassing way to teach.
video went 2x after Lex introduction.
This guy looks like peter petrelli
Machinegun….
Appreciate the upload. This lecture series is amazing. Dropping a comment about secure multi-party computation. This sounds like an amazing application for the blockchain technology. Dunno if this is brought up after the introduction of secure multi-party computation. had to pause when he described it.
Great Talk. Regarding sewage system and water supply, have a look what the Romans were capable of doing. They were 1000s years ahead of their time.
"Does that make sense?"
…um
The sewage analogy was brilliant.
Could this have any relevance to Coronavirus contact tracing?
He spoke to quickly, don't know what was pursuing him. He could have been signaled to slow down a bit.
4:06 The common cold… Kind of far sighted
As someone that works in healthcare, this is fascinating.
Singularitynet are building a Decentralised AI Ecosystem Built on these ideas. A Must to check out!!!
I was there! One of the best talks I have seen
He seems so exciting to convey his idea to the students, what a researcher ! Great job!
Thank you Lex!
Ultimately AI will protect human privacy (from other humans anyway) because it will replace every institution that requires such information for legitimate purposes, and have no need to share it with any humans to carry out those purposes.
30:38 will this work with non-linearities which are quite important for neural nets?
Greatly enjoying your book Andrew!
Solid
Andrew task is already in 2.x
Maybe is a bad question, what happen if massive malicious group enter hudge quantity of fake data in that kind of system?
Got his book and will hopefully start exploring it soon 🙂 Excellent talk Andrew – thumbs up!