Deep Learning State of the Art (2019) - MIT

New lecture on recent developments in deep learning that are defining the state of the art in our field (algorithms, applications, and tools). This is not a complete list, but hopefully includes a good sampling of new exciting ideas. For more lecture videos visit our website or follow code tutorials on our GitHub repo.

INFO:

OUTLINE:
0:00 - Introduction
2:00 - BERT and Natural Language Processing
14:00 - Tesla Autopilot Hardware v2+: Neural Networks at Scale
16:25 - AdaNet: AutoML with Ensembles
18:32 - AutoAugment: Deep RL Data Augmentation
22:53 - Training Deep Networks with Synthetic Data
24:37 - Segmentation Annotation with Polygon-RNN++
26:39 - DAWNBench: Training Fast and Cheap
29:06 - BigGAN: State of the Art in Image Synthesis
30:14 - Video-to-Video Synthesis
32:12 - Semantic Segmentation
36:03 - AlphaZero & OpenAI Five
43:34 - Deep Learning Frameworks
44:40 - 2019 and beyond

CONNECT:
- If you enjoyed this video, please subscribe to this channel.

[lexfridman]

I'm excited about recent developments in NLP, deep RL, speeding up training/inference, big GANs, powerful DL frameworks, and real-world application of DL in driving 370k+ Tesla HW2 cars! What else would you like to see covered?

[derasor]

It could be very insightful to go back to this talk in a couple of years time, and see how these ideas developped.

[wtaylorjr]

This is fantastic. I am trying to create a storytelling system using LSTM s and a corpus of self-written works. Thank you for this Mr. Fridman.

[SaidakbarP]

Lex's summary is so true:
Stochastic gradient descent and backpropagation are still backbones of the current state of the art AI techniques. Therefore, we need some innovations to see leaps in the field.
Thank you Lex!

[pratikkala]

This is the most valuable thing that I saw in 2019.
This guy have the same voice that the Breaking Bad's actor, Jesse Pinkman.

[nebimertaydin]

This is the most valuable thing that I saw in 2019.

[JousefM]

Thanks a ton Lex! You're one of the guys who brought me from Mech. Engineering to AI :)

[alaaalatif]

Great review on recent advance in deep learning! Would be great to see a similar review of current (immediate) challenges e.g. limited numerical extrapolation abilities, multi-task learning...etc.

[JeDi___]

Thanks for the lecture. Also, well edited (erasing pauses). Funny to see you transform to Men in Blue compared to when you started the lecture two years ago. Looking good

[vobjects]

So funny how Lex refers to the fast.ai folks as renegade reserchers :-D

[josephakindiraneverthings]

Awesome, , thanks
The intro is invaluable and very helpful

[tobedecided]

40:40 Is it just me or is Lex slowly increasing his excitement when talking about OpenAI & DOTA 2
Anyway, great work and thank you

[alienkishorekumar]

Didn't understand much. But I'm excited. Moving forwards.

[kodee]

Amazing content Lex, always very informative to help filter the firehose of research papers.

[eliasxu]

Very happy to see the prosperity of deep learning. I hope I can excavate the biggest potential of DL in the field of computational advertising.

[megadebtification]

Thank you Lex !! Always great to learn from you

[josy]

Awesome Lex, are you planning on doing the same for 2020?

[igor]

Awesome video. Are there good links to videos on other developments not mentioned, e.g. in healthcare and agriculture?

[ohyoyshozebulo]

It would be great if you add to description links from the presentation!

[katanaking]

I was absolutely shocked by how brilliant these approaches to deep learning where. I'm absolutely excited to see what we can come up with next