Privacy Preserving AI (Andrew Trask) | MIT Deep Learning Series ai technology for education

by adminhuahinsunvilla3sd



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:

Images related to the topic ai technology for education

Privacy Preserving AI (Andrew Trask) | MIT Deep Learning Series

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

Related Posts

33 comments

Lex Fridman 01/03/2022 - 8:20 Chiều

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

Reply
lgn 01/03/2022 - 8:20 Chiều

He is talking so fast. Or is the video accelerated by default?

Reply
Roscoe Torbenson 01/03/2022 - 8:20 Chiều

Cool to see Nick Mullen has gotten into computer science

Reply
shakib yazdani 01/03/2022 - 8:20 Chiều

What a fantastic talk, enjoyed every minute of it. He also wants the talk himself, which is quite interesting.

Reply
Macknight Xu 01/03/2022 - 8:20 Chiều

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?

Reply
Joshua Lilley 01/03/2022 - 8:20 Chiều

I love this

Reply
Sidrah Abdullah 01/03/2022 - 8:20 Chiều

Excellent talk! Really enjoyed it.

Reply
Ronald Logan 01/03/2022 - 8:20 Chiều

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.

Reply
Levon Minasian 01/03/2022 - 8:20 Chiều

The most complex thing here is to not look at the line integral on the blackboard:))

Reply
denzil studios 01/03/2022 - 8:20 Chiều

heeey im getting 4 mid video ads in one go now ;( (great intro to ppML)

Reply
Peter Shu 01/03/2022 - 8:20 Chiều

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.

Reply
arvinder singh 01/03/2022 - 8:20 Chiều

video went 2x after Lex introduction.

Reply
Nigel Foster-Jones 01/03/2022 - 8:20 Chiều

This guy looks like peter petrelli

Reply
Katarina Luna diCamella 01/03/2022 - 8:20 Chiều

Machinegun….

Reply
Aaron 01/03/2022 - 8:20 Chiều

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.

Reply
Detlef Eckert 01/03/2022 - 8:20 Chiều

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.

Reply
lonward 01/03/2022 - 8:20 Chiều

"Does that make sense?"

…um

Reply
Charis Apostolidis 01/03/2022 - 8:20 Chiều

The sewage analogy was brilliant.

Reply
JimJamRazzMaTaz 01/03/2022 - 8:20 Chiều

Could this have any relevance to Coronavirus contact tracing?

Reply
Create Channel 01/03/2022 - 8:20 Chiều

He spoke to quickly, don't know what was pursuing him. He could have been signaled to slow down a bit.

Reply
Poutrelle 01/03/2022 - 8:20 Chiều

4:06 The common cold… Kind of far sighted

Reply
MilaStatic 01/03/2022 - 8:20 Chiều

As someone that works in healthcare, this is fascinating.

Reply
Real AGI 01/03/2022 - 8:20 Chiều

Singularitynet are building a Decentralised AI Ecosystem Built on these ideas. A Must to check out!!!

Reply
Stephan Gravert 01/03/2022 - 8:20 Chiều

I was there! One of the best talks I have seen

Reply
胡安啦 01/03/2022 - 8:20 Chiều

He seems so exciting to convey his idea to the students, what a researcher ! Great job!

Reply
Shaan M. Khan 01/03/2022 - 8:20 Chiều

Thank you Lex!

Reply
Zrebbesh 01/03/2022 - 8:20 Chiều

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.

Reply
Олександр Лапшин 01/03/2022 - 8:20 Chiều

30:38 will this work with non-linearities which are quite important for neural nets?

Reply
Oscar Bastardo 01/03/2022 - 8:20 Chiều

Greatly enjoying your book Andrew!

Reply
Albert James 01/03/2022 - 8:20 Chiều

Solid

Reply
shivam sisodiya 01/03/2022 - 8:20 Chiều

Andrew task is already in 2.x

Reply
doomurk max 01/03/2022 - 8:20 Chiều

Maybe is a bad question, what happen if massive malicious group enter hudge quantity of fake data in that kind of system?

Reply
Jousef Murad 01/03/2022 - 8:20 Chiều

Got his book and will hopefully start exploring it soon 🙂 Excellent talk Andrew – thumbs up!

Reply

Leave a Comment